Spare power automatic switching locking judgment method and system

Abstract

The invention provides a spare power automatic switching locking judgment method and system, can effectively prevent spare power automatic switching misoperation, and relates to the technical field of power system protection and automation. According to the method, on the basis of traditional current locking logic, artificial intelligence and big data analysis technologies are combined, live detection device locking is introduced, and the three technologies are fused to form a self-adaptive multiple locking criterion, so that the reliability of the spare power automatic switching device under various load conditions is improved. And through a split-phase detection method and non-contact measurement, the current detection precision is further improved, and the risk of misoperation is reduced. The problem of misoperation caused by too small current under the light load condition can be solved, the locking logic reliability of the spare power automatic switching device is greatly improved, and a more reliable guarantee is provided for stable operation of a power system.

Description

Technical Field

[0001] The invention relates to the technical field of power system protection and automation, and in particular to a method and system for judging standby automatic switching lockout. Background Art

[0002] The backup automatic switch device is an important safety automatic device in the power system. When the main power supply of the system disappears for various reasons, the backup power supply will automatically start to ensure that the power load of the system and the users will not lose power. The busbars of the substation are powered by unrelated power supplies. After one power supply trips, the backup automatic switch device can quickly restore the power supply of the busbar. The backup automatic switch function has a simple implementation principle and low maintenance cost. It is an economical and effective measure to ensure the reliability and continuity of power supply of the power grid. However, due to electrical interference, equipment failure, operating conditions and human settings, the backup automatic switch device may malfunction.

[0003] In order to improve the reliability of the device operation, current interlocking logic is usually adopted, that is, when the current detection exceeds the set threshold, the interlocking is activated, and the backup automatic transfer device will not be activated regardless of whether the line voltage detection is normal; when the current detection is lower than the set threshold, the interlocking is invalid and the backup automatic transfer device can be started.

[0004] However, in actual applications, due to changes in load, the incoming current will fluctuate. Under light load conditions, the output signal of the current transformer is weak. When it is lower than the current lockout threshold, a false operation will occur. In addition, small current signals are easily covered by noise, making it difficult for the device to accurately judge the actual state of the line, increasing the risk of false operation. Existing methods to prevent false operation of the backup automatic re-start mainly focus on adding more auxiliary contacts or detection criteria as lockout conditions when the bus loses pressure, so as to improve the reliability of the backup automatic re-start. Common methods are as follows.

[0005] 1) Increase the number of parallel auxiliary contacts of the isolating switch and circuit breaker in the secondary voltage switching circuit. When one auxiliary contact has poor contact or is damaged, the other contact can be connected normally to ensure that the TV secondary voltage switching plug-in has voltage output and prevent the backup automatic switching device from malfunctioning due to bus TV disconnection.

[0006] 2) Add detection criteria, by adding signal detection at different positions in the standby automatic re-entry lockout logic, so as to improve the reliability of the standby automatic re-entry action. The detection power line extraction voltage is lower than the set voltage as the starting condition. When the standby automatic re-entry meets other action conditions and the working power supply voltage is lower than the set voltage, that is, the power supply low voltage setting value, the standby automatic re-entry can act.

[0007] 3) Improve the current blocking threshold algorithm. For example, the phase current mutation calculation unit calculates the percentage of the phase current mutation of the first bus and the second bus; outputs the incoming line standby automatic switching action or the graded standby automatic switching action according to the bus voltage acquisition unit, the phase current acquisition unit and the phase current mutation calculation unit.

[0008] In the current solution, adding auxiliary contacts cannot fundamentally solve the problem. Although the dual nodes improve the reliability of the TV secondary voltage measurement results, the completion of a logical action requires the contacts of the relevant relays to be opened and closed multiple times, and the probability of relay damage is very high, which reduces the correctness of the standby automatic transfer device and reduces the power supply reliability. Although adding detection criteria can improve the reliability of the standby automatic transfer device to a certain extent, there is still a risk of secondary busbar pressure loss for light loads and various complex situations that occur in actual operation, and it is difficult to effectively and accurately detect the current signal.

[0009] For example, the invention patent with the authorization number CN107329027B discloses a method for judging TV line break in double-bus automatic backup devices suitable for light loads. It mainly determines whether a TV line break has occurred by judging the incoming line status, voltage status, and current status of the bus. It combines the changes in the current and voltage of the bus, and uses logical operations and delayed anti-interference processing to judge whether the TV line is broken under light load conditions. However, according to the comparative document, when the load is light, the incoming current of the bus may be very small, close to or lower than the set "no-current set value", and the current signal is very weak. At this time, the signal is weak, and the signal detected by the current sensor may be interfered by noise, resulting in inaccurate current value measurement. Especially under light load conditions, the amplitude of the noise and the signal is not much different, which can easily lead to misjudgment and make it impossible to accurately judge the actual state of the line. In addition, the document only uses simple logical operations to judge the incoming line status. Fixed logical operations cannot accurately cope with complex scenarios such as sudden load changes and changes in line impedance. Summary of the invention

[0010] Purpose of the invention: In order to overcome the problem of false operation of the standby automatic start-up device under various complex light-load conditions, the present invention provides a standby automatic start-up device lockout judgment method, which proposes a new standby automatic start-up device lockout logic control system, which improves the reliability of the standby automatic start-up device action from multiple aspects such as energized state monitoring and intelligent line judgment. Based on this, the present invention also provides a standby automatic start-up device lockout judgment system.

[0011] Technical solution: According to a first aspect of the present invention, a method for judging the automatic lockout of a standby device is provided, the method comprising:

[0012] Collect the three-phase line current and three-phase line voltage in a certain section of the transmission line in the power system, and store the three-phase line current and three-phase line voltage data in different time periods; perform analog-to-digital conversion on the formed three-phase line current sampling sequence to obtain the corresponding digital current signal FA , F B and F C , where A, B and C are three-phase lines;

[0013] Using a historical current signal data set during the normal operation of the power system as input, learning a neural network model to obtain the trained neural network model, and outputting a feature vector set representing the line operation state;

[0014] Input the three-phase line current and three-phase line voltage collected in real time into the trained neural network model, output feature vectors of multiple states, compare the obtained feature vectors of the multiple states with the feature vector set representing the line operation state, so as to obtain abnormal signals of the multiple states; determine whether there is a fault with light load risk according to the abnormal signal of each state in combination with the first logic judgment program;

[0015] If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal;

[0016] Otherwise, if it is determined that there is a fault with light load risk, the preset threshold value in the light load state is dynamically adjusted according to the preset live detection threshold value in normal operation; and the live state of the corresponding phase is determined according to the preset threshold value in the light load state, so as to obtain the second result judgment formula;

[0017] According to the first result judgment formula and the second result judgment formula, it is judged whether the line is in a normal or abnormal state, and different responses are made to avoid malfunction of the backup automatic transfer device.

[0018] Further, including:

[0019] The characteristic vectors of the obtained multiple states are compared with the characteristic vector set representing the line operation state, so as to obtain abnormal signals of multiple states, specifically including: current mutation signal F ΔI , waveform distortion signal F D , voltage mutation signal F V , frequency abnormal signal frequency abnormal signal F K .

[0020] Further, including:

[0021] The abnormal signal of each state is combined with the first logic judgment program to determine whether there is a fault with light load risk, wherein the first logic judgment program is expressed as:

[0022] F S =(F ΔI ×F v ×F k ×F D );

[0023] When F S =0 means the line load is in normal state; when F S =1, it indicates that a line light load risk fault is detected.

[0024] Further, including:

[0025] If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal, specifically including:

[0026] When the digital current signal F A , F B and F C When current is detected in all three phases of the circuit, a normal signal is output; when current is not detected in any phase, a fault signal is output; the digital current signal is compared with the first logic judgment program F S Through the AND gate logic connection, the first result judgment formula is expressed as:

[0027] F f1 =(F A +F B +F C )×F S ;

[0028] Among them, F f1 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f1 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0029] Further, including:

[0030] If it is determined that there is a fault with light load risk, dynamically adjusting the preset threshold value in the light load state according to the preset live detection threshold value during normal operation specifically includes:

[0031] The transmission line voltage at this time under the light load state is obtained, and the output voltage signal V is obtained after signal amplification, filtering, and digitization. X (t), where X = A, B, C, i.e. V A (t), V B (t), V C (t);

[0032] Dynamically adjust the live detection threshold V under light load conditions ad , the charged detection threshold V ad It is used to correct the preset threshold under light load state to ensure that a weak electric field signal is detected under light load state to avoid false locking, which is expressed as:

[0033] V ad =V th ×K L ;

[0034] If V X (t)≥V ad , then it is determined that the phase is in a live state; otherwise, the phase line is not live; correspondingly, the detection result of each phase is converted into digital signals F1, F2, F3.

[0035] Further, including:

[0036] The charging state of the corresponding phase is determined according to the preset threshold value under the light load state, thereby obtaining a second result judgment formula, which is expressed as:

[0037] F f2 =[(F A +F B +F C )+(F1+F2+F3)]×F S ;

[0038] Among them, F f2 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f2 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0039] On the other hand, the present invention also provides a standby automatic lockout judgment system, which includes: a detection device, a live indicator, a line risk assessment module, a threshold adjustment module, and a result judgment module;

[0040] The detection device includes three, which are respectively used to collect the three-phase line current and three-phase line voltage in a certain section of the transmission line in the power system, and store the three-phase line current and three-phase line voltage data in different time periods; perform analog-to-digital conversion on the formed three-phase line current sampling sequence to obtain the corresponding digital current signal F A , F B and F C , where A, B and C are three-phase lines;

[0041] Line risk assessment module, including training unit, risk assessment unit and judgment unit;

[0042] The training unit is used to use the historical current signal data set during the normal operation of the power system as input to learn the neural network model, obtain the trained neural network model, and output a feature vector set representing the line operation state;

[0043] The risk assessment unit is used to input the three-phase line current and three-phase line voltage collected in real time into the trained neural network model, output the feature vectors of multiple states, compare the obtained feature vectors of the multiple states with the feature vector set representing the line operation state, so as to obtain abnormal signals of the multiple states; and determine whether there is a fault with light load risk according to the abnormal signal of each state in combination with the first logic judgment program;

[0044] The judgment unit is used to judge whether there is a fault with light load risk according to the first logic judgment program. If it is judged that there is no fault with light load risk, a first result judgment formula is set in combination with the obtained digital current signal; otherwise, the live indicator is used to collect the output voltage signal of the current line, and the threshold adjustment module is used to adjust the preset threshold of the live indicator, and the live state of the corresponding phase is judged according to the preset threshold under the light load state, so as to obtain a second result judgment formula;

[0045] The result judgment module is used to judge whether the line is in a normal or abnormal state according to the first result judgment formula and the second result judgment formula, and make different responses to avoid malfunction of the standby automatic transfer device.

[0046] Further, including:

[0047] The characteristic vectors of the obtained multiple states are compared with the characteristic vector set representing the line operation state, so as to obtain abnormal signals of multiple states, specifically including: current mutation signal F ΔI , waveform distortion signal F D , voltage mutation signal F V , frequency abnormal signal frequency abnormal signal F K .

[0048] Further, including:

[0049] The abnormal signal of each state is combined with the first logic judgment program to determine whether there is a fault with light load risk, wherein the first logic judgment program is expressed as:

[0050] F S =(F ΔI ×F v ×F k ×F D );

[0051] When F S =0 means the line load is in normal state; when F S =1, it indicates that a line light load risk fault is detected.

[0052] Further, including:

[0053] If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal, specifically including:

[0054] When the digital current signal F A , F B and F C When current is detected in all three phases of the circuit, a normal signal is output; when current is not detected in any phase, a fault signal is output; the digital current signal is compared with the first logic judgment program F S Through the AND gate logic connection, the first result judgment formula is expressed as:

[0055] F f1 =(F A +F B +F C )×F S ;

[0056] Among them, F f1 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f1 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0057] Further, including:

[0058] The method of using the live indicator to collect the output voltage signal of the current line and using a threshold adjustment module to adjust the preset threshold of the live indicator includes:

[0059] The transmission line voltage at this time under the light load state is obtained, and the output voltage signal V is obtained after signal amplification, filtering, and digitization. X (t), where X = A, B, C, i.e. V A (t), V B (t), V C (t);

[0060] Dynamically adjust the live detection threshold V under light load conditions ad , the charged detection threshold V ad It is used to correct the preset threshold under light load state to ensure that a weak electric field signal is detected under light load state to avoid false locking, which is expressed as:

[0061] V ad =V th ×K L ;

[0062] If V X (t)≥V ad, then it is determined that the phase is in a live state; otherwise, the phase line is not live; correspondingly, the detection result of each phase is converted into digital signals F1, F2, F3.

[0063] Further, including:

[0064] The charging state of the corresponding phase is determined according to the preset threshold value under the light load state, thereby obtaining a second result judgment formula, which is expressed as:

[0065] F f2 =[(F A +F B +F C )+(F1+F2+F3)]×F S ;

[0066] Among them, F f2 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f2 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0067] Beneficial effects: Compared with the prior art, the present invention has the following advantages: The present invention provides a method for preventing the false operation of the backup automatic switch by integrating live detection and intelligent line status judgment. It combines the use of live indicators to detect voltage signals, adjusts the threshold, and combines the detection of current conditions to form a double locking criterion, which significantly improves the reliability of the backup automatic switch under various load conditions; and the use of non-contact live detection and comprehensive analysis of real-time current signals can effectively reduce the risk of false operation caused by light load;

[0068] The neural network model is used to learn and classify historical current data in real time, realizing intelligent judgment of line status and abnormality detection.

[0069] Therefore, the method proposed in the present application not only improves the reliability of the locking logic of the backup automatic transfer device under light load conditions, but also can quickly identify and respond to abnormal conditions of the line, enhance the stability and safety of the power system, reduce the troubleshooting time, and improve the accuracy and effectiveness of the overall protection system. The light load condition refers to the situation in which the bus current is small due to load changes during the operation of the power system line, which will cause the backup automatic transfer device to malfunction. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a flow chart of the automatic lockout judgment method for standby according to an embodiment of the present invention;

[0071] Figure 2 This is a schematic diagram of the working state of the live detection device according to an embodiment of the present invention;

[0072] Figure 3 This is a current blocking logic diagram for live detection according to an embodiment of the present invention;

[0073] Figure 4 This is a flow chart of preventing false operation of standby automatic switching by integrating live detection and intelligent line status judgment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0076] Example 1

[0077] like Figure 1 As shown, a method for judging the automatic lockout of a standby device is provided, the method comprising:

[0078] S1 collects the three-phase line current and three-phase line voltage in a certain section of the transmission line in the power system, and stores the three-phase line current and three-phase line voltage data in different time periods; performs analog-to-digital conversion on the formed three-phase line current sampling sequence to obtain the corresponding digital current signal F A , F B and F C , where A, B and C are three-phase lines.

[0079] Among them, the overcurrent detection device detects the three-phase line current i A (t), i B (t), i C (t) is sampled, and the voltage detection device samples the line voltage u A (t)u B (t),u C (t) is sampled, and then the original sampled value is stored to obtain the three-phase line current sampling sequence i A (n), i B (n), i C (n), where n represents the sampling point at the current moment and n-1 represents the previous 1 / f s The sampling point at time, f s The analog-to-digital converter (ADC) in the internal logic circuit current detection device converts the current detection state digital signal into a digital signal F A , FB and F C .

[0080] S2 uses the historical current signal data set during the normal operation of the power system as input to learn the neural network model, obtain the trained neural network model, and output a feature vector set representing the line operation status.

[0081] This embodiment does not limit the specific neural network model, as long as accurate classification is achieved. Preferably, SVM is used for classification, and the historical current signal data during the normal operation of the power system is learned through the SVM algorithm to extract the feature vector set X to represent the line operation status. The feature vector X described in the embodiment of the present invention includes but is not limited to parameters such as current amplitude, waveform change rate, and spectrum characteristics, which can effectively reflect the normal and abnormal states of the line, and the real-time collected current data i is analyzed through these feature vectors. A (t), i B (t), i C (t) Classification is performed to identify the operating status of the line and output the corresponding digital signal for subsequent locking judgment.

[0082] After fault detection, the present invention automatically stores fault data and related information in a database, and regularly conducts secondary learning of historical fault data through the SVM algorithm. This process will continuously optimize the feature vector set and the decision boundary of the classifier to improve the model's ability to identify abnormal line status, thereby enhancing the protection accuracy of the entire system.

[0083] The present invention adopts streaming data access technology to collect the current signal i in real time. A (t), i B (t), i C (t) Seamless storage and management to ensure the real-time and integrity of data. At the same time, the system supports efficient query and analysis of large-scale historical data, providing strong data support for fault diagnosis and model optimization.

[0084] S3 inputs the three-phase line current and three-phase line voltage collected in real time into the trained neural network model, outputs the feature vectors of multiple states, compares the obtained feature vectors of the multiple states with the feature vector set characterizing the line operation state, thereby obtaining abnormal signals of the multiple states; and determines whether there is a fault with light load risk based on the abnormal signal of each state in combination with the first logic judgment program.

[0085] Specifically, the specific comparison method is not limited in the embodiment of the present invention. The average value of multiple data in different states can be used as a threshold, or the value can be taken upward or downward within the threshold range, and compared with the line information collected in real time as the threshold range; other numerical comparison methods can also be used, such as using time for correspondence, such as comparing the information data of the state of the line at this time with the data collected at the corresponding time point. If they are the same, it is normal, otherwise it is determined to be abnormal, and abnormal signal data sets of multiple states are obtained.

[0086] If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal;

[0087] Otherwise, if it is determined that there is a fault with light load risk, the preset threshold under the light load state is dynamically adjusted according to the preset live detection threshold during normal operation; and the live state of the corresponding phase is judged according to the preset threshold under the light load state, thereby obtaining the second result judgment formula.

[0088] Specifically, the real-time collected voltage u A (t)u B (t),u C (t) and current data i A (t), i B (t), i C (t) Input the SVM classification system, combine the historical feature data and current waveform analysis, and the SVM classification system outputs multiple state digital signals, including: current mutation signal F ΔI , waveform distortion signal F D , voltage mutation signal F V , frequency abnormal signal frequency abnormal signal F K ,These signals are input into the logic judgment program and connected through the "AND" gate.,That is, when the current, voltage, frequency, and waveform are all abnormal, it indicates that the line has a light load risk fault at this time.

[0089] F S =(F ΔI ×F v ×F k ×F D );

[0090] When F S =0 means the line load is in normal state; when F S =1, it indicates that a line light load risk fault is detected.

[0091] In this embodiment, if it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal, specifically including:

[0092] When the digital current signal FA , F B and F C When current is detected in all three phases of the circuit, a normal signal is output; when current is not detected in any phase, a fault signal is output; the digital current signal is compared with the first logic judgment program F S Through the AND gate logic connection, the first result judgment formula is expressed as:

[0093] F f1 =(F A +F B +F C )×F S ;

[0094] Among them, F f1 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f1 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0095] Further, in this embodiment, if it is determined that there is a fault with a light load risk, the preset threshold value in the light load state is dynamically adjusted according to the preset live detection threshold value in normal operation, such as Figure 4 As shown, specifically including:

[0096] The transmission line voltage at this time under the light load state is obtained, and the output voltage signal V is obtained after signal amplification, filtering, and digitization. X (t), where X = A, B, C, i.e. V A (t), V B (t), V C (t).

[0097] In this embodiment, combined with the real-time operation status of the line determined by the SVM, when the line is detected to be in a light load or abnormal state, the system will dynamically adjust the threshold of the live detection device. The dynamically adjusted live detection threshold V ad Calculated by the following formula, where: V th K is the preset live detection threshold during normal operation. L is the light load correction factor, K L The value is obtained based on the attenuation degree of the electric field signal of the real-time line compared with the historical signal and the laboratory experience value test, ranging from 0 to 1, and is used to correct the preset threshold under light load conditions to ensure that weaker electric field signals are detected under light load conditions to avoid false locking.

[0098] That is, dynamically adjust the power detection threshold V under light load state ad , the charged detection threshold V adIt is used to correct the preset threshold under light load state to ensure that a weak electric field signal is detected under light load state to avoid false locking, which is expressed as:

[0099] V ad =V th ×K L ;

[0100] If V X (t)≥V ad , then it is determined that the phase is in a live state; otherwise, the phase line is not live; correspondingly, the detection result of each phase is converted into digital signals F1, F2, F3.

[0101] In this embodiment, when the phase line is energized, the output signal is F x =1(x=1, 2, 3); when the phase line is not energized, the output signal is F x =0 (x=1, 2, 3), finally, the signals output by the three power indicators are sent to the subsequent logic judgment program.

[0102] Based on the current detection and intelligent line load judgment, three live displays are used to measure the live state of the three-phase circuit. When current is detected in all three-phase lines, a normal signal "0" is output; when no current is detected in any phase, a fault signal "1" is output; current detection and live detection are logically connected through an "OR" gate, and in addition, they are logically connected with the line risk signal Fs of the SVM through an "AND" gate, such as Figure 3 As shown, specifically:

[0103] The charged state of the corresponding phase is determined according to the preset threshold value under the light load state, thereby obtaining the second result determination formula, which is expressed as:

[0104] F f2 =[(F A +F B +F C )+(F1+F2+F3)]×F S ;

[0105] Among them, F f2 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f2 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0106] S4 determines whether the line is in a normal or abnormal state according to the first result judgment formula and the second result judgment formula, and makes different responses to avoid malfunction of the backup automatic transfer device.

[0107] In this embodiment, when F f1=0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f1 =1, indicating that a fault or abnormality is detected, the backup automatic transfer device will automatically trigger the lock to avoid malfunction; or

[0108] When F f2 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f2 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0109] Example 2

[0110] The present invention also provides a standby automatic lockout judgment system, which includes: a detection device, a live indicator, a line risk assessment module, a threshold adjustment module, and a result judgment module;

[0111] The detection device includes a current detection device and a voltage detection device, which are respectively used to collect the three-phase line current and the three-phase line voltage in a certain section of the power transmission line in the power system, and store the three-phase line current and the three-phase line voltage data in different time periods; the formed three-phase line current sampling sequence is converted into analog-to-digital to obtain the corresponding digital current signal F A , F B and F C , where A, B and C are three-phase lines;

[0112] Line risk assessment module, including training unit, risk assessment unit and judgment unit;

[0113] The training unit is used to use the historical current signal data set during the normal operation of the power system as input to learn the neural network model, obtain the trained neural network model, and output a feature vector set representing the line operation state;

[0114] The risk assessment unit is used to input the three-phase line current and three-phase line voltage collected in real time into the trained neural network model, output the feature vectors of multiple states, compare the obtained feature vectors of the multiple states with the feature vector set representing the line operation state, so as to obtain abnormal signals of the multiple states; and determine whether there is a fault with light load risk according to the abnormal signal of each state in combination with the first logic judgment program;

[0115] The judgment unit is used to judge whether there is a fault with light load risk according to the first logic judgment program. If it is judged that there is no fault with light load risk, the first result judgment formula is set in combination with the obtained digital current signal; otherwise, the live indicator is used to collect the output voltage signal of the current line, and the threshold adjustment module is used to adjust the preset threshold of the live indicator, and the live state of the corresponding phase is judged according to the preset threshold under the light load state, so as to obtain the second result judgment formula.

[0116] The principle of use of the charged indicator is as follows Figure 2 As shown, the live detection device mainly uses the electric field coupling principle between the high-voltage electric field and the sensor to perform inductive (non-contact) measurement at a safe distance. When the measured line is energized, the "A, B, C" three-phase indicator lights are on, the "operation indicator light is off, and a forced locking signal is output; when the measured line is not energized, the "A, B, C" three-phase indicator lights are all off, the "operation" indicator light is on, and the locking signal is released at the same time, and the equipment can be operated.

[0117] The result judgment module is used to judge whether the line is in a normal or abnormal state according to the first result judgment formula and the second result judgment formula, and make different responses to avoid malfunction of the standby automatic transfer device.

[0118] Further, including:

[0119] The characteristic vectors of the obtained multiple states are compared with the characteristic vector set representing the line operation state, so as to obtain abnormal signals of multiple states, specifically including: current mutation signal F ΔI , waveform distortion signal F D , voltage mutation signal F V , frequency abnormal signal frequency abnormal signal F K .

[0120] Further, including:

[0121] The abnormal signal of each state is combined with the first logic judgment program to determine whether there is a fault with light load risk, wherein the first logic judgment program is expressed as:

[0122] F S =(F ΔI ×F v ×F k ×F D );

[0123] When F S =0 means the line load is in normal state; when F S =1, it indicates that a line light load risk fault is detected.

[0124] Further, including:

[0125] If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal, specifically including:

[0126] When the digital current signal F A , F B and F C When current is detected in all three phases of the circuit, a normal signal is output; when current is not detected in any phase, a fault signal is output; the digital current signal is compared with the first logic judgment program F S Through the AND gate logic connection, the first result judgment formula is expressed as:

[0127] F f1 =(F A +F B +F C )×F S ;

[0128] Among them, F f1 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f1 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

[0129] Further, including:

[0130] The method of using the live indicator to collect the output voltage signal of the current line and using a threshold adjustment module to adjust the preset threshold of the live indicator includes:

[0131] The transmission line voltage at this time under the light load state is obtained, and the output voltage signal V is obtained after signal amplification, filtering, and digitization. X (t), where X = A, B, C, i.e. V A (t), V B (t), V C (t);

[0132] Dynamically adjust the live detection threshold V under light load conditions ad , the charged detection threshold V ad It is used to correct the preset threshold under light load state to ensure that a weak electric field signal is detected under light load state to avoid false locking, which is expressed as:

[0133] V ad =V th ×K L ;

[0134] If V X (t)≥V ad, then it is determined that the phase is in a live state; otherwise, the phase line is not live; correspondingly, the detection result of each phase is converted into digital signals F1, F2, F3.

[0135] Further, including:

[0136] The charging state of the corresponding phase is determined according to the preset threshold value under the light load state, thereby obtaining a second result judgment formula, which is expressed as:

[0137] F f2 =[(F A +F B +F C )+(F1+F2+F3)]×F S ;

[0138] Among them, F f2 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f2 =1, indicating that a fault or abnormality is detected, the backup automatic transfer device will automatically trigger the lock to avoid malfunction

[0139] Other technical features corresponding to the standby automatic re-entry locking judgment system described in the present invention are similar to the standby automatic re-entry locking judgment method and will not be repeated here.

[0140] It should be noted that since the storage medium provided in the embodiment of the present application is the storage medium used to implement the method of the embodiment of the present application, based on the method introduced in the embodiment of the present application, the person skilled in the art can understand the specific structure and deformation of the storage medium, so it is not repeated here. All storage media used in the method of the embodiment of the present application belong to the scope of protection of this application.

[0141] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0142] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0143] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0144] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0145] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0146] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0147] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0148] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for judging the automatic lockout of a backup device, characterized in that: The method includes: Collect the three-phase line current and three-phase line voltage in a certain section of the transmission line in the power system, and store the three-phase line current and three-phase line voltage data in different time periods; perform analog-to-digital conversion on the formed three-phase line current sampling sequence to obtain the corresponding digital current signal F A , F B and F C , where A, B and C are three-phase lines; Using a historical current signal data set during the normal operation of the power system as input, learning a neural network model to obtain the trained neural network model, and outputting a feature vector set representing the line operation state; Input the three-phase line current and three-phase line voltage collected in real time into the trained neural network model, output feature vectors of multiple states, compare the obtained feature vectors of the multiple states with the feature vector set representing the line operation state, so as to obtain abnormal signals of the multiple states; determine whether there is a fault with light load risk according to the abnormal signal of each state in combination with the first logic judgment program; If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal; Otherwise, if it is determined that there is a fault with light load risk, the preset threshold value in the light load state is dynamically adjusted according to the preset live detection threshold value in normal operation; and the live state of the corresponding phase is determined according to the preset threshold value in the light load state, so as to obtain the second result judgment formula; According to the first result judgment formula and the second result judgment formula, it is judged whether the line is in a normal or abnormal state, and different responses are made to avoid malfunction of the backup automatic transfer device.

2. The method for judging the automatic lockout of the standby power supply according to claim 1, characterized in that: The characteristic vectors of the obtained multiple states are compared with the characteristic vector set representing the line operation state, so as to obtain abnormal signals of multiple states, specifically including: current mutation signal F ΔI , waveform distortion signal F D , voltage mutation signal F V , frequency abnormal signal frequency abnormal signal F K .

3. The method for judging the automatic lockout of the standby power supply according to claim 2, characterized in that: The abnormal signal of each state is combined with the first logic judgment program to determine whether there is a fault with light load risk, wherein the first logic judgment program is expressed as: F S =(F ΔI ×F v ×F k ×F D ); When F S =0 means the line load is in normal state; when F S =1, it indicates that a line light load risk fault is detected.

4. The method for judging the automatic lockout of the backup power supply according to claim 3 is characterized in that: If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal, specifically including: When the digital current signal F A , F B and F C When current is detected in all three phases of the circuit, a normal signal is output; when current is not detected in any phase, a fault signal is output; the digital current signal is compared with the first logic judgment program F S Through the AND gate logic connection, the first result judgment formula is expressed as: F f1 =(F A +F B +F C )×F S ; Among them, F f1 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f1 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

5. The method for judging the automatic lockout of the standby power supply according to claim 3, characterized in that: If it is determined that there is a fault with light load risk, dynamically adjusting the preset threshold value in the light load state according to the preset live detection threshold value during normal operation specifically includes: The transmission line voltage at this time under the light load state is obtained, and the output voltage signal V is obtained after signal amplification, filtering, and digitization. X (t), where X = A, B, C, i.e. V A (t), V B (t), V C (t); Dynamically adjust the live detection threshold V under light load conditions ad , the charged detection threshold V ad It is used to correct the preset threshold under light load state to ensure that a weak electric field signal is detected under light load state to avoid false locking, which is expressed as: V ad =V th ×K L ; If V X (t)≥V ad , then it is determined that the phase is in a live state; otherwise, the phase line is not live; correspondingly, the detection result of each phase is converted into digital signals F1, F2, F3.

6. The method for judging the automatic lockout of the standby power supply according to claim 5, characterized in that: The charging state of the corresponding phase is determined according to the preset threshold value under the light load state, thereby obtaining a second result judgment formula, which is expressed as: <h2 style=";text-align:left;direction:ltr">F<h2 style=";text-align:left;direction:ltr"> f2 <h2 style=";text-align:left;direction:ltr"> ×[(F<h2 style=";text-align:left;direction:ltr"> A <h2 style=";text-align:left;direction:ltr"> +F<h2 style=";text-align:left;direction:ltr"> B <h2 style=";text-align:left;direction:ltr"> +F<h2 style=";text-align:left;direction:ltr"> C <h2 style=";text-align:left;direction:ltr"> )+(F1+F2+F3)]×F<h2 style=";text-align:left;direction:ltr"> S <h2 style=";text-align:left;direction:ltr"> ; Among them, F f2 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f2 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

7. A self-closing lockout judgment system, characterized in that: The system includes: a detection device, a live indicator, a line risk assessment module, a threshold adjustment module, and a result judgment module; The detection device includes three, which are respectively used to collect the three-phase line current and three-phase line voltage in a certain section of the transmission line in the power system, and store the three-phase line current and three-phase line voltage data in different time periods; perform analog-to-digital conversion on the formed three-phase line current sampling sequence to obtain the corresponding digital current signal F A , F B and F C , where A, B and C are three-phase lines; Line risk assessment module, including training unit, risk assessment unit and judgment unit; The training unit is used to use the historical current signal data set during the normal operation of the power system as input to learn the neural network model, obtain the trained neural network model, and output a feature vector set representing the line operation state; The risk assessment unit is used to input the three-phase line current and three-phase line voltage collected in real time into the trained neural network model, output the feature vectors of multiple states, compare the obtained feature vectors of the multiple states with the feature vector set representing the line operation state, so as to obtain abnormal signals of the multiple states; and determine whether there is a fault with light load risk according to the abnormal signal of each state in combination with the first logic judgment program; The judgment unit is used to judge whether there is a fault with light load risk according to the first logic judgment program. If it is judged that there is no fault with light load risk, a first result judgment formula is set in combination with the obtained digital current signal; otherwise, the live indicator is used to collect the output voltage signal of the current line, and the threshold adjustment module is used to adjust the preset threshold of the live indicator, and the live state of the corresponding phase is judged according to the preset threshold under the light load state, so as to obtain a second result judgment formula; The result judgment module is used to judge whether the line is in a normal or abnormal state according to the first result judgment formula and the second result judgment formula, and make different responses to avoid malfunction of the standby automatic transfer device.

8. The automatic lockout judgment system according to claim 7 is characterized in that: The characteristic vectors of the obtained multiple states are compared with the characteristic vector set representing the line operation state, so as to obtain abnormal signals of multiple states, specifically including: current mutation signal F ΔI , waveform distortion signal F D , voltage mutation signal F V , frequency abnormal signal frequency abnormal signal F K .

9. The automatic lockout judgment system according to claim 8 is characterized in that: The abnormal signal of each state is combined with the first logic judgment program to determine whether there is a fault with light load risk, wherein the first logic judgment program is expressed as: F S =(F ΔI ×F v ×F k ×F D ); When F S =0 means the line load is in normal state; when F S =1, it indicates that a line light load risk fault is detected.

10. The automatic lockout judgment system according to claim 9 is characterized in that: If it is determined that there is no underload risk fault, a first result judgment formula is set in combination with the obtained digital current signal, specifically including: When the digital current signal F A , F B and F C When current is detected in all three phases of the circuit, a normal signal is output; when current is not detected in any phase, a fault signal is output; the digital current signal is compared with the first logic judgment program F S Through the AND gate logic connection, the first result judgment formula is expressed as: F f1 =(F A +F B +F C )×F S ; Among them, F f1 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f1 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

11. The automatic lockout judgment system according to claim 9, characterized in that: The method of using the live indicator to collect the output voltage signal of the current line and using a threshold adjustment module to adjust the preset threshold of the live indicator includes: The transmission line voltage at this time under the light load state is obtained, and the output voltage signal V is obtained after signal amplification, filtering, and digitization. X (t), where X = A, B, C, i.e. V A (t), V B (t), V C (t); Dynamically adjust the live detection threshold V under light load conditions ad , the charged detection threshold V ad It is used to correct the preset threshold under light load state to ensure that a weak electric field signal is detected under light load state to avoid false locking, which is expressed as: V ad =V th ×K L ; If V X (t)≥V ad , then it is determined that the phase is in a live state; otherwise, the phase line is not live; correspondingly, the detection result of each phase is converted into digital signals F1, F2, F3.

12. The automatic lockout judgment system according to claim 11, characterized in that: The charging state of the corresponding phase is determined according to the preset threshold value under the light load state, thereby obtaining a second result judgment formula, which is expressed as: <h2 style=";text-align:left;direction:ltr">F<h2 style=";text-align:left;direction:ltr"> f2 <h2 style=";text-align:left;direction:ltr"> =[(F<h2 style=";text-align:left;direction:ltr"> A <h2 style=";text-align:left;direction:ltr"> +F<h2 style=";text-align:left;direction:ltr"> B <h2 style=";text-align:left;direction:ltr"> +F<h2 style=";text-align:left;direction:ltr"> C <h2 style=";text-align:left;direction:ltr"> )+(F1+F2+F3)]×F<h2 style=";text-align:left;direction:ltr"> S <h2 style=";text-align:left;direction:ltr"> ; Among them, F f2 =0 means the line is in normal state, and the standby automatic switching device maintains the current operating state; when F f2 =1, it indicates that a fault or abnormality is detected, and the backup automatic transfer device will automatically trigger the lock to avoid false operation.

Images