Power grid equipment voltage abnormality feature extraction method and system based on factor analysis method

Abstract

The present disclosure relates to the field of power grid monitoring, and particularly relates to a power grid equipment voltage anomaly feature extraction method and system based on a factor analysis method, the method comprising the following steps: obtaining a power grid equipment section bus three-phase voltage value and an alarm signal; obtaining a section bus three-phase voltage value based on normal distribution statistics of random components in historical power grid equipment standardized samples to obtain a sample random component fluctuation lower limit and a fluctuation upper limit, performing factor analysis extraction to obtain a random component, and judging whether the random component exceeds the fluctuation lower limit and the fluctuation upper limit; if the fluctuation lower limit and the fluctuation upper limit are exceeded, then combining the alarm signal to perform voltage anomaly research and judgment to achieve power grid equipment voltage anomaly feature extraction. The present disclosure can perform voltage recovery research and judgment, voltage anomaly research and judgment, and whether it is a non-shielded event according to the bus three-phase voltage of the power grid equipment combined with the voltage alarm signal data.

Description

Technical Field

[0001] This disclosure relates to the field of power grid monitoring, specifically to a method and system for extracting voltage anomaly features of power grid equipment based on factor analysis. Background Technology

[0002] In addition to normal bus load voltage data, voltage anomalies in power grid equipment also include spike anomalies, setpoint anomalies, and pattern anomalies. To extract these anomalies, methods such as k-means clustering, anomaly identification based on inherent attributes, and legality identification based on statistical patterns are commonly used. For example, K-means clustering analysis of feature sequences can be used to determine transformer substation types. Furthermore, different pre-judgments and decisions can be made based on data type, value, and external value correlation attributes, such as first-level and second-level line power flow limit violations and voltage upper and lower limits. For ordinary limit violations, a preliminary anomaly can be predicted; if an impossible limit is exceeded, it can be directly identified as bad data, and the identification process can terminate with a result. Values ​​must follow certain rules (enumerated values, external table values, etc.); data that does not meet these rules can also be identified as bad data. Alternatively, based on different time intervals of regular data, maximum and minimum thresholds can be set according to their fluctuation range, and then the data within each interval can be filtered. This method can filter out most bad data. This discrimination method can be used to verify power generation and load data for regions or provinces / cities.

[0003] The strength of confirmatory factor analysis lies in its ability to allow researchers to explicitly describe the details of a theoretical model. So what does a researcher want to describe? We previously mentioned that due to measurement error, researchers need to use multiple measures. When using multiple measures, we face the issue of the "quality" of these measures, i.e., validity testing. Validity testing examines whether a measure has significant loadings on its designed factors and no significant loadings on factors unrelated to it. Of course, we might further examine whether a measure tool has single-method bias, or whether there are "sub-factors" among some measures. All these tests require researchers to explicitly describe the relationships between measures, factors, and residuals. This description of relationships is called a measurement model. Quality testing of the measurement model is a necessary step before hypothesis testing.

[0004] Therefore, existing technologies introduce factor analysis to decompose the bus load curve into basic components characterizing the normal time-series variation of the curve and random components characterizing the abnormal or random fluctuations of the curve data; simultaneously, based on the random components of the load curve, methods for identifying abnormal data are provided. Judgment Criteria. Judging whether a curve contains outliers based on whether the fluctuation of random components crosses the line has limited effectiveness in identifying outliers in fixed-value data or pattern outliers. Moreover, it can only be used when the sample size is very large to ignore the impact of a small number of outliers on the extraction of basic components of the sample. Summary of the Invention

[0005] This disclosure provides a method and system for extracting voltage anomaly features from power grid equipment based on factor analysis, which can solve at least one of the problems mentioned in the background art. To solve the above-mentioned technical problems, this disclosure provides the following technical solution:

[0006] As one aspect of this disclosure, a method for extracting voltage anomaly features of power grid equipment based on factor analysis is provided, comprising the following steps:

[0007] Acquire the three-phase voltage values ​​and alarm signals of the busbar at the cross-section of the power grid equipment;

[0008] Based on the normal distribution statistics of random components in the standardized samples of historical power grid equipment, the lower limit and upper limit of random component fluctuation are obtained. The random component is extracted by factor analysis of the three-phase voltage value of the cross-section bus. It is then determined whether the random component exceeds the lower limit and upper limit of fluctuation.

[0009] If the fluctuation exceeds the lower and upper limits, voltage anomaly analysis is performed in conjunction with alarm signals to extract voltage anomaly characteristics of power grid equipment.

[0010] Preferably, after determining whether the three-phase voltage values ​​of the cross-section busbar exceed the lower and upper limits of the fluctuation, the following steps are also included:

[0011] If the fluctuation does not exceed the lower and upper limits, an anomaly recovery analysis is performed in conjunction with the alarm signal to generate an anomaly recovery event.

[0012] Preferably, anomaly recovery analysis is performed to generate anomaly recovery events, including:

[0013] Check for any voltage anomaly markers on the power grid equipment;

[0014] If the voltage anomaly marker is found, an anomaly recovery event is generated, and it is determined whether the three-phase voltage values ​​of the current section and the section of the previous minute have recovered to the threshold fluctuation range composed of the lower fluctuation limit and the upper fluctuation limit. If not, no anomaly recovery event is generated.

[0015] Preferably, the process of performing anomaly recovery analysis to generate anomaly recovery events further includes:

[0016] After generating an abnormal recovery event, it is also necessary to calculate the duration of the abnormality. If it is a bus stop, the duration only needs to be calculated from the occurrence of the abnormality to the stop point; otherwise, the duration from the occurrence time to the recovery time is calculated.

[0017] Preferably, the method further includes the following steps:

[0018] Determine whether at least one of the three-phase voltage values ​​of the cross-section busbar is close to zero. If so, conduct anomaly tracking and analysis.

[0019] Preferably, anomaly tracking and analysis includes the following steps:

[0020] Check for high-voltage fuse delay markers on power grid equipment;

[0021] If the delay marker can be found, it is determined whether the time of the abnormality has reached the delay threshold. If it has, it is determined whether all three phases are close to zero and whether there is an alarm signal. If they are all close to zero and accompanied by an alarm signal, voltage abnormality analysis is performed. Otherwise, the analysis of the current power grid equipment is terminated.

[0022] If the delay marker is not found, check if there is a voltage anomaly marker for the power grid equipment. If the voltage anomaly marker is found, determine if the anomaly type is low current grounding and if all three phases are close to zero, and whether the main transformer and bus branch switches connected to the bus are all open. If all conditions are met, generate an anomaly tracking and reporting event; otherwise, end the analysis of the current equipment.

[0023] Preferably, the voltage anomaly assessment includes:

[0024] Check if there are any voltage anomaly markers on the power grid equipment;

[0025] If the voltage anomaly marker is not found, determine whether the three-phase voltage value of the section in the previous minute exceeds the limit. If so, it indicates that the bus voltage is abnormal and enter the abnormal event analysis. Otherwise, end the analysis of the current power grid equipment.

[0026] If one phase of the three-phase voltage value of the busbar at the cross section exceeds the lower limit, and the other two phases exceed the upper limit, or if the upper limit is not obvious but exceeds the floating upper limit compared with the cross section voltage value in the previous 5 minutes, it is determined to be a small current grounding.

[0027] If at least one phase of the three-phase voltage value of the busbar cross-section exceeds the lower limit, and the voltage values ​​of the remaining phases do not exceed the upper limit of the floating range compared with the cross-section voltage value in the previous 5 minutes, then it is determined that the high-voltage fuse has blown.

[0028] If the time of the abnormality of the power grid equipment falls within the shielding time interval of any one of the three: bus interval, equipment, and telemetry, then only a shielding event will be generated.

[0029] As another aspect of this disclosure, a system for extracting voltage anomaly features of power grid equipment based on factor analysis is provided, comprising:

[0030] The voltage acquisition module acquires the three-phase voltage values ​​and alarm signals of the busbar at the power grid equipment section.

[0031] The upper and lower limit determination module obtains the lower and upper limits of the random component fluctuation based on the normal distribution statistics of the random components in the standardized samples of historical power grid equipment, obtains the three-phase voltage values ​​of the cross-section bus through factor analysis to extract the random components, and determines whether the random components exceed the lower and upper limits of fluctuation.

[0032] The voltage anomaly feature extraction module, if the voltage exceeds the lower and upper fluctuation limits, combines the alarm signal to perform voltage anomaly analysis in order to extract the voltage anomaly features of the power grid equipment.

[0033] As another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for extracting voltage anomaly features of power grid equipment based on factor analysis.

[0034] As another aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method for extracting voltage anomaly features of power grid equipment based on factor analysis.

[0035] Compared to existing technologies, this disclosure can perform voltage recovery analysis, voltage anomaly analysis, and determine whether an event is unshielded based on the three-phase bus voltage of power grid equipment combined with voltage alarm signal data. Embodiments of this disclosure also determine the type of abnormal event in the power grid equipment by statistically analyzing the duration of the anomaly. Analysis based on alarm signals can identify abnormal setpoint data or abnormal pattern data, without affecting the impact of a small amount of abnormal data on the extraction of basic sample components. Attached Figure Description

[0036] Figure 1 This is a flowchart of the method for extracting voltage anomaly features of power grid equipment based on factor analysis in Embodiment 1 of this disclosure;

[0037] Figure 2 This is a schematic block diagram of the power grid equipment voltage anomaly feature extraction system based on factor analysis in Embodiment 2 of this disclosure. Detailed Implementation

[0038] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0039] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0040] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0041] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0042] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further.

[0043] In addition, this disclosure also provides a system, electronic device, computer-readable storage medium, and program for extracting voltage anomaly features of power grid equipment based on factor analysis. All of the above can be used to implement any of the voltage anomaly feature extraction methods for power grid equipment based on factor analysis provided in this disclosure. The corresponding technical solutions and descriptions are described in the relevant section of the method and will not be repeated here.

[0044] The method for extracting voltage anomaly features from power grid equipment based on factor analysis can be executed by a computer or other device capable of performing this extraction. For example, the method can be executed by a terminal device, server, or other processing device. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. In some possible implementations, this method can be implemented by a processor calling computer-readable instructions stored in memory.

[0045] Example 1

[0046] As one aspect of this disclosure, a method for extracting voltage anomaly features of power grid equipment based on factor analysis is provided, such as... Figure 1 As shown, it includes the following steps:

[0047] S10. Obtain the three-phase voltage values ​​and alarm signals of the busbar at the power grid equipment section;

[0048] S20. Based on the normal distribution statistics of the random components in the standardized samples of historical power grid equipment, the lower limit and upper limit of the random component fluctuation are obtained. The three-phase voltage values ​​of the cross-section bus are obtained and the random components are extracted by factor analysis. It is then determined whether the random components exceed the lower limit and upper limit of the fluctuation.

[0049] S30. If the fluctuation exceeds the lower and upper limits, voltage anomaly analysis is performed in conjunction with the alarm signal to extract voltage anomaly features of power grid equipment.

[0050] Based on the above configuration, this disclosure embodiment can perform voltage recovery analysis, voltage anomaly analysis, and determine whether it is a non-shielded event based on the three-phase bus voltage of the power grid equipment combined with voltage alarm signal data.

[0051] The steps of each embodiment of this disclosure will be described in detail below.

[0052] S10. Obtain the three-phase voltage values ​​and alarm signals of the busbar at the power grid equipment section;

[0053] Among them, the three-phase voltage value of the bus section of the power grid equipment can be obtained by means of, but not limited to, the following: install current transformers on the three phases of the bus, and determine the three-phase voltage value of the bus by dividing the current value and resistance value obtained by the current transformers. The three-phase voltage value at a certain moment is called the three-phase voltage value of the bus section.

[0054] In some embodiments, the following steps may be performed first: busbar equipment data filtering and busbar maintenance assessment. The busbar equipment data filtering rules are as follows:

[0055] ①. Equipment voltage level is 110kV and below (including 110kV)

[0056] ②. Busbar equipment is not labeled.

[0057] ③. The device name does not contain "legacy" or "virtual".

[0058] ④. The busbar equipment lacks maintained telemetry definition data;

[0059] ⑤. Busbar maintenance is required.

[0060] The busbar maintenance assessment rules are as follows:

[0061] ①. Obtain all connected bays of the same voltage level in the same substation through bus node topology.

[0062] ②. Any interval status that falls under one of the following three categories is acceptable: hot standby, cold standby, or maintenance.

[0063] ③. Hot standby: switch open; Cold standby: both switch and disconnector open; Maintenance: both switch and disconnector open, grounding disconnector closed.

[0064] The alarm signals can include telemetry alarm signals, remote signaling alarm signals, and displacement alarm signals, as detailed below:

[0065] The telemetry alarm signal is displayed in the window and the signal status is one of the three: "beyond the normal lower limit", "beyond the accident upper limit", or "beyond the accident lower limit".

[0066] Remote signaling alarm signal: The alarm level is "accident" or "abnormal" and the signal status is not "maintenance". The alarm signal is an accident or abnormality of the protection device. The expression is "(bus differential)?((protection|measurement)|automatic transfer|measurement and control)(device|operation)(abnormal|fault)|TV disconnection|arc suppression coil|grounding(alarm)?".

[0067] Displacement alarm signal: The signal status is neither "maintenance" nor "blocked".

[0068] S20. Based on the normal distribution statistics of the random components in the standardized samples of historical power grid equipment, the lower limit and upper limit of the random component fluctuation are obtained. The three-phase voltage values ​​of the cross-section bus are obtained and the random components are extracted by factor analysis. It is then determined whether the random components exceed the lower limit and upper limit of the fluctuation.

[0069] The process of obtaining the lower and upper limits of random component fluctuations based on normal distribution statistics of random components in a standardized sample of historical power grid equipment includes the following steps:

[0070] Normal distribution statistics were performed on the random components in the standardized sample of historical power grid equipment. The sample random component matrix containing the three-phase voltage values ​​of n buses is as follows:

[0071] ;

[0072] In the formula, This represents the random component of the load at time i of the three-phase voltage value of the j-th bus in the sample. This represents the random component of the three-phase voltage value of the nth bus at time p; based on this, the mean of the normal distribution of the sample random component is obtained. and standard deviation The components are as follows:

[0073] ;

[0074] According to the Raida criterion, the lower limit of fluctuation of random components in a sample. and upper limit of fluctuation for:

[0075] ;

[0076] ;

[0077] The steps for obtaining the random components by factor analysis of the three-phase voltage values ​​of the cross-section busbar are as follows:

[0078] Basic components and random components are extracted from the standardized sample X. The standardized sample is obtained by filtering the original collected data and deleting and splicing obvious abnormal data caused by power grid equipment failure or communication equipment failure to form a new standardized sample.

[0079] The extraction of basic components and random components from standardized sample X can be achieved in the following manner:

[0080] Calculate standardized samples covariance matrix :

[0081] ;

[0082] ;

[0083] in, It is the average load of the sample at each time point. The expression is: ; The standard deviation of the load at each time point of the sample is given. e is an n-dimensional column vector with all elements being 1.

[0084] Calculate the standardized sample covariance matrix eigenvalues and the corresponding unit orthogonal eigenvectors .

[0085] Then, the factor loading matrices of the factor analysis model for the standardized sample X are estimated respectively. Common factor matrix and special factor matrix :

[0086] ;

[0087] ;

[0088] ;

[0089] After performing inverse normalization, random components can be obtained. :

[0090] .

[0091] S30. If the fluctuation exceeds the lower and upper limits, voltage anomaly analysis is performed in conjunction with the alarm signal to extract voltage anomaly features of power grid equipment.

[0092] In this embodiment, compared with the above Has it fallen to the lower limit of fluctuation? and upper limit of fluctuation If the voltage exceeds the specified range, it is considered an anomaly. The voltage anomaly is then analyzed in conjunction with the aforementioned alarm signals to identify voltage anomaly characteristics, such as high-voltage fuse blowout or busbar shutdown.

[0093] As a preferred embodiment, after determining whether the three-phase voltage value of the cross-section busbar exceeds the lower and upper limits of the fluctuation, the following steps are also included:

[0094] If the fluctuation does not exceed the lower and upper limits, an anomaly recovery analysis is performed in conjunction with the alarm signal to generate an anomaly recovery event.

[0095] As a preferred implementation, anomaly recovery analysis is performed to generate anomaly recovery events, including:

[0096] Check for voltage anomaly markers on power grid equipment; this can be done by searching the Redis cache.

[0097] If the voltage anomaly marker is found, an anomaly recovery event is generated, and it is determined whether the three-phase voltage values ​​of the current section and the section of the previous minute have recovered to the threshold fluctuation range composed of the lower fluctuation limit and the upper fluctuation limit. If not, no anomaly recovery event is generated.

[0098] As a preferred implementation, performing anomaly recovery analysis to generate anomaly recovery events also includes:

[0099] After generating an abnormal recovery event, it is also necessary to calculate the duration of the abnormality. If it is a bus stop, the duration only needs to be calculated from the occurrence of the abnormality to the stop point; otherwise, the duration from the occurrence time to the recovery time is calculated.

[0100] In a preferred embodiment, the method further includes the following steps:

[0101] Determine whether at least one of the three-phase voltage values ​​of the cross-section busbar is close to zero. If so, conduct anomaly tracking and analysis.

[0102] As a preferred implementation method, anomaly tracking and analysis includes the following steps:

[0103] Check if a high-voltage fuse deactivation delay flag exists for a power grid device; for example, check if the high-voltage fuse deactivation delay flag ("ROBOT_CACHE-[AREANO]-[EQUIP_ID]_DYYCNEW_delay") exists in the Redis cache.

[0104] If the delay marker can be found, it is determined whether the time of the abnormality has reached the delay threshold. If it has, it is determined whether all three phases are close to zero and whether there is an alarm signal. If they are all close to zero and accompanied by an alarm signal, voltage abnormality analysis is performed. Otherwise, the analysis of the current power grid equipment is terminated.

[0105] If the delay marker is not found, then check if there is a voltage anomaly marker for the power grid equipment, for example...

[0106] ("ROBOT_CACHE-[AREANO]-[EQUIP_ID]_DYYCNEW_occur_time") If the indicated voltage anomaly marker can be found, determine whether the anomaly type is a small current grounding and whether all three phases are close to zero, and whether the main transformer and bus branch switches connected to the bus are all opened. If all conditions are met, generate an anomaly tracking and reporting event; otherwise, end the analysis of the current equipment.

[0107] As a preferred embodiment, the voltage anomaly assessment includes:

[0108] Check if a voltage anomaly flag exists for the power grid equipment; for example, check if a voltage anomaly flag for the equipment exists in the Redis cache.

[0109] ("ROBOT_CACHE-[AREANO]-[EQUIP_ID]_DYYCNEW_occur_time");

[0110] If the voltage anomaly marker is not found, determine whether the three-phase voltage value of the section in the previous minute exceeds the limit. If so, it indicates that the bus voltage is abnormal and enter the abnormal event analysis. Otherwise, end the analysis of the current power grid equipment.

[0111] If one phase of the three-phase voltage value of the busbar at the cross section exceeds the lower limit, and the other two phases exceed the upper limit, or if the upper limit is not obvious but exceeds the floating upper limit compared with the cross section voltage value in the previous 5 minutes, it is determined to be a small current grounding.

[0112] If at least one phase of the three-phase voltage value of the busbar cross-section exceeds the lower limit, and the voltage values ​​of the remaining phases do not exceed the upper limit of the floating range compared with the cross-section voltage value in the previous 5 minutes, then it is determined that the high-voltage fuse has blown.

[0113] If the time of the abnormality of the power grid equipment falls within the shielding time interval of any one of the three: bus interval, equipment, and telemetry, then only a shielding event will be generated.

[0114] Example 2

[0115] As another aspect of this disclosure, a power grid equipment voltage anomaly feature extraction system 100 based on factor analysis is provided, such as... Figure 2 As shown, it includes:

[0116] Voltage acquisition module 1 acquires the three-phase voltage values ​​and alarm signals of the busbar at the power grid equipment section;

[0117] The upper and lower limit determination module 2 obtains the lower and upper limits of the random component fluctuation based on the normal distribution statistics of the random components in the standardized samples of historical power grid equipment, obtains the three-phase voltage values ​​of the cross-section busbar and extracts the random components through factor analysis, and determines whether the random components exceed the lower and upper limits of the fluctuation.

[0118] The voltage anomaly feature extraction module 3, if the voltage exceeds the lower and upper fluctuation limits, combines the alarm signal to perform voltage anomaly analysis in order to extract the voltage anomaly features of the power grid equipment.

[0119] Among them, the three-phase voltage value of the bus section of the power grid equipment can be obtained by means of, but not limited to, the following: install current transformers on the three phases of the bus, and determine the three-phase voltage value of the bus by dividing the current value and resistance value obtained by the current transformers. The three-phase voltage value at a certain moment is called the three-phase voltage value of the bus section.

[0120] In some embodiments, the voltage value acquisition module 1 can also perform the following functions: busbar equipment data filtering and busbar maintenance assessment. The busbar equipment data filtering rules are as follows:

[0121] ①. Equipment voltage level is 110kV and below (including 110kV)

[0122] ②. Busbar equipment is not labeled.

[0123] ③. The device name does not contain "legacy" or "virtual".

[0124] ④. The busbar equipment lacks maintained telemetry definition information data;

[0125] ⑤. Busbar maintenance is required.

[0126] The busbar maintenance assessment rules are as follows:

[0127] ①. Obtain all connected bays of the same voltage level in the same substation through bus node topology.

[0128] ②. Any interval status that falls under one of the following three categories is acceptable: hot standby, cold standby, or maintenance.

[0129] ③. Hot standby: switch open; Cold standby: both switch and disconnector open; Maintenance: both switch and disconnector open, grounding disconnector closed.

[0130] The alarm signals can include telemetry alarm signals, remote signaling alarm signals, and displacement alarm signals, as detailed below:

[0131] The telemetry alarm signal is displayed in the window and the signal status is one of the three: "beyond the normal lower limit", "beyond the accident upper limit", or "beyond the accident lower limit".

[0132] Remote signaling alarm signal: The alarm level is "accident" or "abnormal" and the signal status is not "maintenance". The alarm signal is an accident or abnormality of the protection device. The expression is "(bus differential)?((protection|measurement)|automatic transfer|measurement and control)(device|operation)(abnormal|fault)|TV disconnection|arc suppression coil|grounding(alarm)?".

[0133] Displacement alarm signal: The signal status is neither "maintenance" nor "blocked".

[0134] In the upper and lower limit determination module 2, the lower limit and upper limit of the random component fluctuation are obtained based on the normal distribution statistics of the random components in the standardized samples of historical power grid equipment, including:

[0135] Normal distribution statistics were performed on the random components in the standardized sample of historical power grid equipment. The sample random component matrix containing the three-phase voltage values ​​of n buses is as follows:

[0136] ;

[0137] In the formula, This represents the random component of the load at time i of the three-phase voltage value of the j-th bus in the sample. This represents the random component of the three-phase voltage value of the nth bus at time p; based on this, the mean of the normal distribution of the sample random component is obtained. and standard deviation The components are as follows:

[0138] ;

[0139] According to the Raida criterion, the lower limit of fluctuation of random components in a sample. and upper limit of fluctuation for:

[0140] ;

[0141] ;

[0142] In the upper and lower limit determination module 2, the random components are obtained by factor analysis of the three-phase voltage values ​​of the cross-section busbar as follows:

[0143] Basic components and random components are extracted from the standardized sample X. The standardized sample is obtained by filtering the original collected data and deleting and splicing obvious abnormal data caused by power grid equipment failure or communication equipment failure to form a new standardized sample.

[0144] The extraction of basic components and random components from standardized sample X can be achieved in the following manner:

[0145] Calculate standardized samples covariance matrix :

[0146] ;

[0147] ;

[0148] in, It is the average load of the sample at each time point. The expression is: ; The standard deviation of the load at each time point of the sample is given. e is an n-dimensional column vector with all elements being 1.

[0149] Calculate the standardized sample covariance matrix eigenvalues and the corresponding unit orthogonal eigenvectors .

[0150] Then, the factor loading matrix of the factor analysis model for the standardized sample X is estimated respectively. Common factor matrix and special factor matrix :

[0151] ;

[0152] ;

[0153] ;

[0154] After performing inverse normalization, random components can be obtained. :

[0155] .

[0156] In voltage anomaly feature extraction module 3, the above are compared. Has it fallen to the lower limit of fluctuation? and upper limit of fluctuation If the voltage exceeds the specified range, it is considered an anomaly. The voltage anomaly is then analyzed in conjunction with the aforementioned alarm signals to identify voltage anomaly characteristics, such as high-voltage fuse blowout or busbar shutdown.

[0157] As a preferred embodiment, after determining whether the three-phase voltage value of the cross-section busbar exceeds the lower and upper limits of the fluctuation, the following steps are also included:

[0158] If the fluctuation does not exceed the lower and upper limits, an anomaly recovery analysis is performed in conjunction with the alarm signal to generate an anomaly recovery event.

[0159] As a preferred implementation, anomaly recovery analysis is performed to generate anomaly recovery events, including:

[0160] Check for voltage anomaly markers on power grid equipment; this can be done by searching the Redis cache.

[0161] If the voltage anomaly marker is found, an anomaly recovery event is generated. It is then determined whether the three-phase voltage values ​​of the current section and the section from the previous minute have recovered to the threshold fluctuation range defined by the lower and upper fluctuation limits. If not, no anomaly recovery event is generated. This reduces the likelihood of voltage anomaly identification during power grid accident handling, maintains the operation of normal equipment and ensures normal power supply to important users, plant auxiliary power, and station auxiliary power, and restores power to users and equipment that have experienced power outages as quickly as possible.

[0162] As a preferred implementation, performing anomaly recovery analysis to generate anomaly recovery events also includes:

[0163] After generating an abnormal recovery event, it is also necessary to calculate the duration of the abnormality. If it is a bus stop, the duration only needs to be calculated from the occurrence of the abnormality to the stop point; otherwise, the duration from the occurrence time to the recovery time is calculated. Based on the recovery time, a time assessment can be provided for users to prevent the escalation of power system accidents, prevent grid collapse and large-scale power outages, and restore the normal operation of the power system.

[0164] In a preferred embodiment, the method further includes the following steps:

[0165] Determine whether at least one of the three-phase voltage values ​​of the cross-section busbar is close to zero. If so, conduct anomaly tracking and analysis.

[0166] As a preferred implementation method, anomaly tracking and analysis includes the following steps:

[0167] Check if a high-voltage fuse deactivation delay flag exists for a power grid device; for example, check if the high-voltage fuse deactivation delay flag ("ROBOT_CACHE-[AREANO]-[EQUIP_ID]_DYYCNEW_delay") exists in the Redis cache.

[0168] If the delay marker can be found, it is determined whether the time of the abnormality has reached the delay threshold. If it has, it is determined whether all three phases are close to zero and whether there is an alarm signal. If they are all close to zero and accompanied by an alarm signal, voltage abnormality analysis is performed. Otherwise, the analysis of the current power grid equipment is terminated.

[0169] If the delay marker is not found, then check if there is a voltage anomaly marker for the power grid equipment, for example...

[0170] ("ROBOT_CACHE-[AREANO]-[EQUIP_ID]_DYYCNEW_occur_time") If the indicated voltage anomaly marker can be found, determine whether the anomaly type is a small current grounding and whether all three phases are close to zero, and whether the main transformer and bus branch switches connected to the bus are all opened. If all conditions are met, generate an anomaly tracking and reporting event; otherwise, end the analysis of the current equipment.

[0171] As a preferred embodiment, the voltage anomaly assessment includes:

[0172] Check if the voltage anomaly flag for the power grid equipment exists; for example, check if the voltage anomaly flag for the equipment exists in the Redis cache as follows:

[0173] ("ROBOT_CACHE-[AREANO]-[EQUIP_ID]_DYYCNEW_occur_time");

[0174] If the voltage anomaly marker is not found, determine whether the three-phase voltage value of the section in the previous minute exceeds the limit. If so, it indicates that the bus voltage is abnormal and enter the abnormal event analysis. Otherwise, end the analysis of the current power grid equipment.

[0175] If one phase of the three-phase voltage value of the busbar at the cross section exceeds the lower limit, and the other two phases exceed the upper limit, or if the upper limit is not obvious but exceeds the floating upper limit compared with the cross section voltage value in the previous 5 minutes, it is determined to be a small current grounding.

[0176] If at least one phase of the three-phase voltage value of the busbar cross-section exceeds the lower limit, and the voltage values ​​of the remaining phases do not exceed the upper limit of the floating range compared with the cross-section voltage value in the previous 5 minutes, then it is determined that the high-voltage fuse has blown.

[0177] If the time of the abnormality of the power grid equipment falls within the shielding time interval of any one of the three: bus interval, equipment, and telemetry, then only a shielding event will be generated.

[0178] Example 3

[0179] This disclosure also includes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method of embodiment 1.

[0180] Embodiment 3 of this disclosure is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this disclosure.

[0181] Electronic devices can take the form of general-purpose computing devices, such as server devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0182] The bus includes a data bus, an address bus, and a control bus.

[0183] The memory may include volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0184] The memory may also include program tools having a set (at least one) of program modules, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0185] The processor performs various functional applications and data processing by running computer programs stored in memory.

[0186] Electronic devices can also communicate with one or more external devices (such as keyboards, pointing devices, etc.). This communication can be achieved through input / output (I / O) interfaces. Furthermore, electronic devices can communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapters. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0187] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0188] Example 4

[0189] This disclosure also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method in Embodiment 1.

[0190] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0191] In a possible implementation, this disclosure can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of implementing the method described in Embodiment 1.

[0192] The program code for executing this disclosure can be written in any combination of one or more programming languages, and the program code can be executed entirely on a user device, partially on a user device, as a stand-alone software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0193] Although embodiments of the present disclosure have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present disclosure, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for extracting voltage anomaly features from power grid equipment based on factor analysis, characterized in that, Includes the following steps: The system acquires the three-phase voltage values ​​and alarm signals of the busbar at a power grid equipment section; the alarm signals include telemetry alarm signals, remote signaling alarm signals, and displacement alarm signals; the three-phase voltage values ​​of the busbar at a section are the three-phase voltage values ​​of the busbar at a certain moment. Based on the normal distribution statistics of random components in the standardized samples of historical power grid equipment, the lower limit and upper limit of random component fluctuation are obtained. The random component is extracted by factor analysis of the three-phase voltage value of the cross-section bus. It is then determined whether the random component exceeds the lower limit and upper limit of fluctuation. If the fluctuation exceeds the lower and upper limits, voltage anomaly analysis is performed in conjunction with alarm signals to extract voltage anomaly characteristics of power grid equipment; it is determined whether at least one phase voltage value of the three-phase busbar is close to zero, and if so, anomaly tracking and analysis are performed; including the following steps: Check for high-voltage fuse delay markers on power grid equipment; If the delay marker can be found, it is determined whether the time of the abnormality has reached the delay threshold. If it has, it is determined whether all three phases are close to zero and whether there is an alarm signal. If they are all close to zero and accompanied by an alarm signal, voltage abnormality analysis is performed. Otherwise, the analysis of the current power grid equipment is terminated. If the delay marker is not found, check if there is a voltage anomaly marker for the power grid equipment. If the voltage anomaly marker is found, determine if the anomaly type is low current grounding and if all three phases are close to zero, and whether the main transformer and bus branch switches connected to the bus are all open. If all conditions are met, generate an anomaly tracking and reporting event; otherwise, end the analysis of the current equipment. The voltage anomaly assessment includes: Check if there are any voltage anomaly markers on the power grid equipment; If the voltage anomaly marker is not found, determine whether the three-phase voltage value of the section in the previous minute exceeds the limit. If so, it indicates that the bus voltage is abnormal and enter the abnormal event analysis. Otherwise, end the analysis of the current power grid equipment. If one phase of the three-phase voltage value of the busbar at the cross section exceeds the lower limit, and the other two phases exceed the upper limit, or if the upper limit is not obvious but exceeds the floating upper limit compared with the cross section voltage value in the previous 5 minutes, it is determined to be a small current grounding. If at least one phase of the three-phase voltage value of the busbar cross-section exceeds the lower limit, and the voltage values ​​of the remaining phases do not exceed the upper limit of the floating range compared with the cross-section voltage value in the previous 5 minutes, then it is determined that the high-voltage fuse has blown. If the time of the abnormality of the power grid equipment falls within the shielding time interval of any one of the three: bus interval, equipment, and telemetry, then only a shielding event will be generated.

2. The method for extracting voltage anomaly features of power grid equipment based on factor analysis as described in claim 1, characterized in that, After determining whether the three-phase voltage values ​​of the cross-section busbar exceed the lower and upper limits of the fluctuation, the following steps are also included: If the fluctuation does not exceed the lower and upper limits, an anomaly recovery analysis is performed in conjunction with the alarm signal to generate an anomaly recovery event.

3. The method for extracting voltage anomaly features of power grid equipment based on factor analysis as described in claim 2, characterized in that, Perform anomaly recovery analysis to generate anomaly recovery events, including: Check for voltage anomaly markers on power grid equipment; If the voltage anomaly marker is found, an anomaly recovery event is generated, and it is determined whether the three-phase voltage values ​​of the current section and the section of the previous minute have recovered to the threshold fluctuation range composed of the lower fluctuation limit and the upper fluctuation limit. If the voltage anomaly marker is not found, no anomaly recovery event is generated.

4. The method for extracting voltage anomaly features of power grid equipment based on factor analysis as described in claim 2 or 3, characterized in that, Performing anomaly recovery analysis to generate anomaly recovery events also includes: After generating an abnormal recovery event, it is also necessary to calculate the duration of the abnormality. If it is a bus stop, the duration only needs to be calculated from the occurrence of the abnormality to the stop point; otherwise, the duration from the occurrence time to the recovery time is calculated.

5. A system for extracting voltage anomaly features of power grid equipment based on factor analysis, characterized in that, include: The voltage value acquisition module acquires the three-phase voltage values ​​and alarm signals of the busbar section of the power grid equipment; the alarm signals include telemetry alarm signals, remote signaling alarm signals, and displacement alarm signals; the three-phase voltage values ​​of the busbar section are the three-phase voltage values ​​of the busbar at a certain moment. The upper and lower limit determination module obtains the lower and upper limits of the random component fluctuation based on the normal distribution statistics of the random components in the standardized samples of historical power grid equipment, obtains the three-phase voltage values ​​of the cross-section bus through factor analysis to extract the random components, and determines whether the random components exceed the lower and upper limits of fluctuation. The voltage anomaly feature extraction module, if the voltage exceeds the lower and upper fluctuation limits, combines alarm signals to perform voltage anomaly analysis to extract voltage anomaly features from power grid equipment; it determines whether at least one phase voltage value of the three-phase busbar is close to zero, and if so, performs anomaly tracking and analysis; including the following steps: Check for high-voltage fuse delay markers on power grid equipment; If the delay marker can be found, it is determined whether the time of the abnormality has reached the delay threshold. If it has, it is determined whether all three phases are close to zero and whether there is an alarm signal. If they are all close to zero and accompanied by an alarm signal, voltage abnormality analysis is performed. Otherwise, the analysis of the current power grid equipment is terminated. If the delay marker is not found, check if there is a voltage anomaly marker for the power grid equipment. If the voltage anomaly marker is found, determine if the anomaly type is low current grounding and if all three phases are close to zero, and whether the main transformer and bus branch switches connected to the bus are all open. If all conditions are met, generate an anomaly tracking and reporting event; otherwise, end the analysis of the current equipment. The voltage anomaly assessment includes: Check if there are any voltage anomaly markers on the power grid equipment; If the voltage anomaly marker is not found, determine whether the three-phase voltage value of the section in the previous minute exceeds the limit. If so, it indicates that the bus voltage is abnormal and enter the abnormal event analysis. Otherwise, end the analysis of the current power grid equipment. If one phase of the three-phase voltage value of the busbar at the cross section exceeds the lower limit, and the other two phases exceed the upper limit, or if the upper limit is not obvious but exceeds the floating upper limit compared with the cross section voltage value in the previous 5 minutes, it is determined to be a small current grounding. If at least one phase of the three-phase voltage value of the busbar cross-section exceeds the lower limit, and the voltage values ​​of the remaining phases do not exceed the upper limit of the floating range compared with the cross-section voltage value in the previous 5 minutes, then it is determined that the high-voltage fuse has blown. If the time of the abnormality of the power grid equipment falls within the shielding time interval of any one of the three: bus interval, equipment, and telemetry, then only a shielding event will be generated.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for extracting voltage anomaly features of power grid equipment based on factor analysis as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for extracting voltage anomaly features of power grid equipment based on factor analysis as described in any one of claims 1 to 4.

Images