Equipment temporary risk locking system and method based on multi-time-sequence power grid model

Abstract

The invention discloses an equipment temporary risk locking system and method based on a multi-time-sequence power grid model. The equipment temporary risk locking system comprises a data collection unit, a data processing unit, a model establishment unit, an anomaly analysis unit, an equipment locking unit, a risk early warning unit, an operation and maintenance feedback unit and an unlocking unit. Relates to the technical field of power grid engineering, a model building unit considers power grid operation states with different time attributes, so that a generated multi-time-sequence power grid model can more accurately reflect the real operation condition of a power grid, and the accuracy of anomaly analysis is improved; the equipment locking unit can automatically lock and isolate equipment with a problem when abnormity is detected, so that the abnormal equipment is prevented from causing greater influence on the whole power grid, meanwhile, stable operation of other parts of the system is ensured, and the system has the advantages of real-time monitoring, accurate evaluation, abnormity prediction, risk locking, timely early warning and the like; safety and reliability of power grid equipment can be effectively improved, and powerful technical support is provided for operation and maintenance of a power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid engineering, and in particular to a system and method for temporarily locking equipment risks based on a multi-time sequence power grid model. Background Art

[0002] In power systems, grid stability and the proper functioning of equipment are crucial prerequisites for ensuring power supply. However, due to various factors, such as equipment aging, environmental changes, and human error, equipment may experience anomalies or even failures, seriously impacting the stable operation of the grid. Therefore, real-time monitoring of grid equipment and early warning of anomalies are crucial.

[0003] Existing power grid monitoring systems typically employ a single approach, such as monitoring only device parameters like voltage, current, or temperature, while ignoring the interrelationships between these parameters. Furthermore, existing systems often rely on manual judgment to identify device anomalies, lacking scientific accuracy. Furthermore, when device anomalies occur, existing systems are unable to promptly isolate and address them, potentially leading to the continued impact of the abnormal device on the grid's stable operation.

[0004] Therefore, how to design a temporary risk locking system for equipment based on a multi-time-series power grid model to accurately evaluate equipment stability, predict equipment anomalies, and promptly lock and handle abnormal equipment has become an urgent problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide a temporary risk locking system and method for equipment based on a multi-time-sequence power grid model. By real-time monitoring of equipment anomalies and locking faults, temporary risk analysis of the power grid is performed, early warning notices are generated, early warnings are issued, and risks are handled by relevant personnel to improve the stability and security of the power grid, thereby solving the technical problems raised in the background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A temporary risk locking system for equipment based on a multi-time-sequence power grid model, comprising:

[0008] A data collection unit is used to collect real-time operating status data of the power grid from monitoring sensors preset in the power grid. The real-time operating status data includes voltage, current, frequency, and temperature parameters of the equipment;

[0009] The data processing unit is used to perform stability calculation on the real-time operation status data and obtain the stability index value of the real-time operation status data at the same time node:

[0010] The model building unit is used to build a multi-time series power grid model reflecting the state of the power grid at different time points based on the stability index value obtained by the data processing unit corresponding to the real-time operation status data and in combination with the preset learning and training rules;

[0011] The abnormality analysis unit is used to perform abnormality analysis on the real-time operating status data obtained at the current time node through a multi-time series power grid model. Based on the analysis results, it determines whether the equipment is abnormal, generates a risk signal of a corresponding level for the abnormal equipment, and transmits the risk signal of a corresponding level generated by the abnormal equipment to the equipment locking unit:

[0012] The device locking unit is used to obtain the corresponding abnormal device according to the risk signal transmitted by the abnormality analysis unit, and lock and isolate the abnormal device through a preset abnormality isolation mechanism.

[0013] As a further solution of the present invention: the calculation processing method of the data processing unit is as follows:

[0014] SA1. Obtain the preset rated voltage, rated current, and rated frequency values ​​of the device, as well as the maximum allowable temperature of the device, and mark them as EU, EI, EP, and Wmax, respectively.

[0015] SA2. Mark the voltage parameters, current parameters, frequency parameters, and temperature parameters obtained at the same time node in the real-time operating status data as SU, SI, SP, and SW respectively;

[0016] SA3, through the preset formula:

[0017] UPC=(SU-EU) / EU*100%

[0018] IPC=(SI-EI) / EI*100%

[0019] PPC=(SP-EP) / EP*100%

[0020] WC=SW-Wmax;

[0021] The voltage deviation ratio UPC, current deviation ratio IPC, frequency deviation ratio PPC and temperature difference WC are obtained respectively;

[0022] SA4, through the preset formula:

[0023]

[0024] Calculate the stability index value QW corresponding to the real-time running status data at the same time node;

[0025] Wherein, α1, α2, and α3 are preset weight coefficients, and β is a preset compensation factor.

[0026] As a further solution of the present invention: the model building unit builds the multi-time sequence power grid model in the following manner:

[0027] SS1. Within a plurality of preset specified periods with different time attributes, a number of standard nodes are divided within the corresponding specified periods;

[0028] SS2. Within multiple specified cycles of the same attribute, obtain real-time operating status data collected on each standard node when the device is operating normally, and extract the stability index value of each standard node after processing by the data processing unit;

[0029] SS3, screen out multiple stability index values ​​through the discrete degree analysis algorithm, calculate their corresponding average values, and then mark their values ​​as the stability index mean;

[0030] SS4. Calculate the mean values ​​of the stability indicators corresponding to the specified periods of the same attribute according to the method of step SS3;

[0031] And select the stability index mean with the minimum and maximum values ​​from all stability index means to form the stability index normal interval [QWmin, QWmax];

[0032] QWmin represents the mean of the stability indicator with the smallest median of all stability indicator means; QWmax represents the mean of the stability indicator with the largest median of all stability indicator means;

[0033] SS5. Within multiple specified cycles of the same attribute, obtain the real-time operating status data collected on each standard node when the equipment is operating abnormally, and extract the stability index value of each standard node after processing by the data processing unit;

[0034] SS6. Taking a specified period as an example, the interquartile range method is used to screen out the stability indicator means corresponding to the specified period, and the abnormal risk judgment value of the indicator corresponding to the corresponding stability indicator mean is obtained;

[0035] SS7, and so on, obtain the normal intervals of stability indicators [QWmin, QWmax] and indicator abnormal risk judgment values ​​Z1 and Z2 corresponding to multiple different time attributes, where, in one time attribute, QWmin<QWmax<Z1<Z2;

[0036] Subsequently, the normal intervals of stability indicators [QWmin, QWmax] and the abnormal risk judgment values ​​Z1 and Z2 of indicators corresponding to each time attribute are trained through preset learning and training rules, and a multi-time series power grid model with different time attribute states is generated.

[0037] As a further solution of the present invention: the specific method of step SS3 is as follows:

[0038] Select a specified period and mark the stability index values ​​collected at each standard node as QW j , j = 1, 2, ..., m, m represents the number of standard nodes, j represents the number of standard nodes;

[0039] Then use the formula Calculate the discrete value L0 of m stability index values, among which QW p is the average value of the m stability index values ​​collected;

[0040] Then the discrete value L0 obtained in the specified period is compared with the preset discrete threshold Ly:

[0041] If L0>Ly, it means that the discrete degree of each stability index value is large, and then according to |QW j -QW p |Delete the corresponding stability index value QW in descending order j The remaining discrete values ​​L0 are calculated accordingly until L0≤Ly;

[0042] When L0≤Ly is obtained later, the stability index value QW of the corresponding discrete value L0 is calculated j , and obtain the corresponding stability index values ​​QW j The average of the values ​​is then labeled as the stability indicator mean.

[0043] As a further solution of the present invention: the screening process in step SS6 is as follows:

[0044] SS61. Sort the stability index values ​​in ascending order to form a sequence table;

[0045] SS62. In the sequence table, select the first quartile Q1 and the third quartile Q3;

[0046] SS63, calculate the interquartile range (IQR) by IQR = Q3 - Q1;

[0047] Among them, the interquartile range IQR reflects the dispersion of the middle 50% of the data;

[0048] SS64. The indicator abnormal risk judgment values ​​Z1 and Z2 are obtained through the formula: Z1 = Q1 - t*IQR and Z2 = Q3 + t*IQR, where t is a fixed value.

[0049] As a further solution of the present invention: the abnormality analysis method of the abnormality analysis unit is as follows:

[0050] SB1. Import the real-time operating status data obtained at the current time node into the data processing unit and perform stability calculation processing. Then, the stability index value corresponding to the current time node is obtained and marked as DQW:

[0051] SB2. Import the stability index value corresponding to the current time node into the multi-time-sequence power grid model, and the multi-time-sequence power grid model obtains the time attribute of the real-time operating status data corresponding to the current time node;

[0052] SB3, the multi-time series power grid model obtains the normal range of stability indicators [QWmin, QWmax] and indicator abnormal risk judgment values ​​Z1 and Z2 corresponding to the same time attribute according to the time attribute of the real-time operation status data corresponding to the current time node;

[0053] SB4. The multi-time-series power grid model compares the stability index value corresponding to the current time node with the normal interval of the stability index [QWmin, QWmax] and the abnormal risk judgment values ​​Z1 and Z2 of the index corresponding to the same time attribute, and obtains the corresponding risk signal.

[0054] As a further solution of the present invention: in step SB4:

[0055] If the DQW value is within [QWmin, QWmax], and it includes DQW = QWmin or DQW = QWmax, no risk signal is generated;

[0056] If DQW<QWmin, a level 1 risk signal is generated;

[0057] If DQW>QWmax], a secondary risk signal is generated;

[0058] If QWmax<DQW≤Z1, a level 3 risk signal is generated;

[0059] If Z1<DQW≤Z2, a level 4 risk signal is generated.

[0060] As a further solution of the present invention: also include:

[0061] The risk warning unit is used to generate risk warning notices based on the corresponding level of risk signals, issue warnings to relevant personnel through dispatching recorded calls, and assign relevant personnel to repair locked and isolated equipment;

[0062] The operation and maintenance feedback unit is used for the relevant personnel to send a maintenance completion signal through the unit after the relevant personnel have repaired the locking and isolation equipment;

[0063] The lock release unit is used to enable the data collection unit to obtain the real-time operating status data of the abnormal equipment at the time node when the maintenance end signal is generated according to the maintenance end signal, and the data processing unit performs stability calculation on the real-time operating status data obtained at the time node, and then obtains the stability index value corresponding to the time node, and then imports the stability index value corresponding to the time node into the multi-time series power grid model for abnormality analysis through the abnormality analysis unit, and determines whether to release the lock isolation of the corresponding abnormal equipment according to the analysis results.

[0064] As a further solution of the present invention, the lock release unit is configured to:

[0065] If the analysis result shows that no risk signal is generated, the abnormal device will be released from lock isolation;

[0066] If the analysis result generates a risk signal of the corresponding level, the abnormal equipment will continue to be locked and isolated. At the same time, the risk warning unit will generate a risk warning notice again according to the level corresponding to the risk signal, and a warning will be issued to relevant personnel again through the dispatch recording phone call.

[0067] The present invention also provides a method for temporarily locking equipment risks based on a multi-time-sequence power grid model, which specifically includes the following steps:

[0068] Collect real-time operating status data from the power grid from monitoring sensors preset in the power grid. The real-time operating status data includes voltage, current, frequency, and temperature parameters of the equipment;

[0069] Perform stability calculation on the real-time running status data and obtain the stability index value of the real-time running status data at the same time node:

[0070] Based on the stability index values ​​obtained from the corresponding real-time operating status data and combined with the preset learning and training rules, a multi-time series power grid model that reflects the status of the power grid at different time points is established;

[0071] Perform an anomaly analysis on the real-time operating status data obtained at the current time node through a multi-time series power grid model. Based on the analysis results, determine whether the equipment is abnormal and generate a risk signal of the corresponding level for the abnormal equipment.

[0072] The corresponding abnormal devices are obtained according to the risk signals of the corresponding levels, and the abnormal devices are locked and isolated through the preset abnormal isolation mechanism.

[0073] The present invention also provides a computer device, comprising: one or more processors; the processors are used to store one or more programs; when the one or more programs are executed by the one or more processors, a method for temporarily locking equipment risks based on a multi-time-sequence power grid model is implemented.

[0074] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, a method for temporarily locking equipment risks based on a multi-time sequence power grid model is implemented.

[0075] Beneficial effects of the present invention:

[0076] Real-time monitoring and risk warning: The real-time operating status of equipment in the power grid is continuously monitored through the data collection unit. Combined with the stability calculation and processing of the data processing unit, it can promptly identify abnormal conditions in equipment operation, thereby issuing risk warnings in advance and reducing potential safety hazards.

[0077] Accuracy of multi-time-sequence power grid models: The model building unit takes into account the power grid operation status with different time attributes, so that the generated multi-time-sequence power grid model can more accurately reflect the actual operation status of the power grid and improve the accuracy of anomaly analysis.

[0078] Detailed abnormality analysis: The abnormality analysis unit can not only determine whether the equipment is abnormal, but also output different levels of risk signals according to the different ranges of stability index values. This helps relevant personnel take corresponding measures for different degrees of abnormalities, improving processing efficiency and response speed.

[0079] Equipment locking and isolation mechanism: The equipment locking unit can automatically lock and isolate the problem equipment when an anomaly is detected, preventing the abnormal equipment from causing a greater impact on the entire power grid while ensuring the stable operation of other parts of the system.

[0080] Maintenance feedback and unlocking: The maintenance feedback unit and unlocking unit allow maintenance personnel to signal the end of maintenance after completing repairs, triggering the system to reassess the status of the equipment. If the assessment is normal, the lock is unlocked, ensuring that the equipment can only be put back into use after it is confirmed to be safe.

[0081] Reduced operation and maintenance costs: The automated monitoring system reduces the need for manual inspections. At the same time, refined management reduces the occurrence of accidents such as power outages caused by equipment abnormalities, thereby saving a lot of manpower and material resources and reducing economic losses caused by failures.

[0082] Improve power supply reliability: Through real-time monitoring and timely exception handling, power supply interruptions caused by equipment failures can be minimized, improving the overall power supply reliability of the power grid.

[0083] In summary, the present invention significantly improves the operational safety and reliability of the power grid by combining real-time monitoring, precise analysis and automatic isolation, while optimizing the power grid's operation and maintenance process, saving costs, and providing an efficient and intelligent solution for power grid operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] The present invention will be further described below with reference to the accompanying drawings.

[0085] Figure 1 This is a system block diagram of a device temporary risk locking system and method based on a multi-time sequence power grid model of the present invention.

[0086] Figure 2 It is a flow chart of a model building unit of a device temporary risk locking system and method based on a multi-time sequence power grid model of the present invention. DETAILED DESCRIPTION

[0087] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making any creative efforts shall fall within the scope of protection of the present invention.

[0088] Example 1

[0089] See also Figure 1 and Figure 2 As shown, the present invention is a temporary risk locking system for equipment based on a multi-time sequence power grid model, comprising:

[0090] A data collection unit, configured to collect real-time operating status data of the power grid from monitoring sensors preset in the power grid;

[0091] Real-time operating status data includes voltage, current, frequency, and temperature parameters of the equipment;

[0092] This embodiment uses the data collection unit to collect real-time operating status data of devices in the power grid, including key parameters such as voltage, current, frequency, and temperature, to achieve real-time monitoring of power grid devices;

[0093] Data processing unit, used to perform stability calculations on real-time operating status data:

[0094] The method is as follows:

[0095] SA1. Obtain the rated voltage, rated current, and rated frequency of the equipment and mark them as EU, EI, and EP, respectively.

[0096] At the same time, obtain the maximum allowable temperature of the device and mark it as Wmax;

[0097] The rated voltage, rated current, rated frequency and maximum allowable temperature are all fixed values ​​provided by the relevant equipment manufacturers;

[0098] SA2. Mark the voltage parameters, current parameters, frequency parameters, and temperature parameters obtained at the same time node in the real-time operating status data as SU, SI, SP, and SW respectively;

[0099] SA3. Compare and calculate the voltage parameters, current parameters, and frequency parameters obtained at the same time node in the real-time operating status data with the rated voltage value, rated current value, and rated frequency value corresponding to the equipment, and obtain the corresponding deviation ratio;

[0100] The comparison calculation formula is as follows:

[0101] Voltage deviation ratio UPC = (SU-EU) / EU*100%;

[0102] Current deviation ratio IPC = (SI-EI) / EI*100%;

[0103] Frequency deviation ratio PPC = (SP-EP) / EP*100%;

[0104] For example: If the rated voltage of the device is 220V, and the actual measured voltage is 230V, the voltage deviation ratio is (230-220) / 220*100%;

[0105] SA4. Obtain the temperature parameter in the real-time operating status data at the same time node as the voltage parameter, current parameter, and frequency parameter in step SA3, and calculate the difference between the temperature parameter and the maximum allowable temperature to obtain the temperature difference;

[0106] The difference calculation formula is: temperature difference WC = SW-Wmax;

[0107] SA5, through the formula:

[0108]

[0109] Calculate the stability index value QW corresponding to the real-time running status data at the same time node;

[0110] Where α1, α2, and α3 are preset weight coefficients, and β is a preset compensation factor;

[0111] This embodiment uses a data processing unit to perform stability calculation processing on real-time operating status data to obtain the stability index value of the equipment and accurately evaluate the operating status of the equipment;

[0112] A model building unit is used to build a multi-time series power grid model reflecting the state of the power grid at different time points based on the collected real-time operation status data;

[0113] The specific method is as follows:

[0114] SS1. Within a plurality of preset specified periods with different time attributes, a number of standard nodes are divided within the corresponding specified periods;

[0115] In this embodiment, the designated periods of different time attributes represent the peak period and the off-peak period of power supply and demand of the power grid respectively;

[0116] In addition, the specified periods of different time attributes also represent the power supply and demand cycles of the power grid in different months or seasons;

[0117] SS2. Within multiple specified cycles of the same attribute, obtain real-time operating status data collected on each standard node when the device is operating normally, and extract the stability index value of each standard node after processing by the data processing unit;

[0118] SS3, taking a specified period as an example, the stability index values ​​collected at each standard node are marked as QW j , j = 1, 2, ..., m, m represents the number of standard nodes, j represents the number of standard nodes;

[0119] Then use the formula Calculate the discrete value L0 of m stability index values, where QW p is the average value of the m stability index values ​​collected;

[0120] Then the discrete value L0 obtained in the specified period is compared with the preset discrete threshold Ly:

[0121] If L0>Ly, it means that the discrete degree of each stability index value is large, and then according to |QW j -QW p |Delete the corresponding stability index value QW in descending order j The remaining discrete values ​​L0 are calculated accordingly until L0≤Ly;

[0122] When L0≤Ly is obtained later, the stability index value QW of the corresponding L0 is calculated j , and obtain the corresponding stability index values ​​QW j The average of the values ​​is then labeled as the stability indicator mean;

[0123] SS4. Calculate the mean values ​​of the stability indicators corresponding to the specified periods of the same attribute according to the method of step SS3;

[0124] And select the stability index mean with the minimum and maximum values ​​from all stability index means to form the stability index normal interval [QWmin, QWmax];

[0125] QWmin represents the mean of the stability indicator with the smallest median of all stability indicator means; QWmax represents the mean of the stability indicator with the largest median of all stability indicator means;

[0126] SS5. Within multiple specified cycles of the same attribute, obtain the real-time operating status data collected on each standard node when the equipment is operating abnormally, and extract the stability index value of each standard node after processing by the data processing unit;

[0127] SS6. Taking a specified period as an example, the interquartile range method is used to screen out the stability indicator means corresponding to the specified period, and the abnormal risk judgment value of the indicator corresponding to the corresponding stability indicator mean is obtained;

[0128] The screening process is as follows:

[0129] SS61. Sort the stability index values ​​in ascending order to form a sequence table;

[0130] SS62. In the sequence table, select the first quartile Q1 and the third quartile Q3;

[0131] SS63, calculate the interquartile range (IQR) by IQR = Q3 - Q1;

[0132] Among them, the interquartile range IQR reflects the dispersion of the middle 50% of the data;

[0133] SS64. Obtain the indicator abnormal risk judgment values ​​Z1 and Z2 using the formula: Z1 = Q1 - t*IQR and Z2 = Q3 + t*IQR, where t is a fixed value.

[0134] SS7, and so on, obtain the normal intervals of stability indicators [QWmin, QWmax] and indicator abnormal risk judgment values ​​Z1 and Z2 corresponding to multiple different time attributes, where, in one time attribute, QWmin<QWmax<Z1<Z2;

[0135] Then, the normal intervals of stability indicators [QWmin, QWmax] and the abnormal risk judgment values ​​Z1 and Z2 of indicators corresponding to each time attribute are trained through the preset learning training rules, and a multi-time series power grid model with different time attribute states is generated;

[0136] This embodiment establishes a multi-time series power grid model to predict possible abnormal conditions of equipment based on historical data and real-time data, and discover potential risks in advance;

[0137] The abnormality analysis unit is used to perform abnormality analysis on the real-time operating status data obtained at the current time node through a multi-time series power grid model:

[0138] The specific method is as follows:

[0139] SB1. Import the real-time operating status data obtained at the current time node into the data processing unit and perform stability calculation processing. Then, the stability index value corresponding to the current time node is obtained and marked as DQW:

[0140] SB2. Import the stability index value corresponding to the current time node into the multi-time-sequence power grid model, and the multi-time-sequence power grid model obtains the time attribute of the real-time operating status data corresponding to the current time node;

[0141] SB3, the multi-time series power grid model obtains the normal range of stability indicators [QWmin, QWmax] and indicator abnormal risk judgment values ​​Z1 and Z2 corresponding to the same time attribute according to the time attribute of the real-time operation status data corresponding to the current time node;

[0142] SB4, the multi-time series power grid model compares the stability index value corresponding to the current time node with the stability index normal interval [QWmin, QWmax] and the index abnormal risk judgment values ​​Z1 and Z2 corresponding to the same time attribute;

[0143] If the DQW value is within [QWmin, QWmax], and it includes DQW = QWmin or DQW = QWmax, no risk signal is generated;

[0144] If DQW<QWmin, a level 1 risk signal is generated;

[0145] If DQW>QWmax], a secondary risk signal is generated;

[0146] If QWmax<DQW≤Z1, a level 3 risk signal is generated;

[0147] If Z1<DQW≤Z2, a level 4 risk signal is generated;

[0148] The risk warning unit is used to generate risk warning notices based on the corresponding level of risk signals, issue warnings to relevant personnel through dispatching recorded calls, and assign relevant personnel to repair locked and isolated equipment;

[0149] In this embodiment, the risk warning unit generates a risk warning notice according to the level corresponding to the risk signal, and issues a warning to relevant personnel through a dispatch recording phone call, notifying the maintenance personnel in time to handle the matter;

[0150] This embodiment effectively improves the safety and reliability of power grid equipment through functions such as real-time monitoring, accurate assessment, anomaly prediction, risk locking, and timely warning.

[0151] Example 2

[0152] As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of this embodiment differs from that of the first embodiment only in that this embodiment further includes:

[0153] The device locking unit is used to obtain the corresponding abnormal device according to the risk signal transmitted by the abnormality analysis unit, and lock and isolate the abnormal device through a preset abnormality isolation mechanism;

[0154] In this embodiment, when an abnormal situation is detected, the device locking unit can lock and isolate the abnormal device to prevent the fault from spreading and ensure the stable operation of the power grid.

[0155] Example 3

[0156] As the third embodiment of the present invention, when the present application is specifically implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments. The technical solution of this embodiment differs from the first and second embodiments only in that this embodiment also includes:

[0157] The operation and maintenance feedback unit is used for the relevant personnel to send a maintenance completion signal through the unit after the relevant personnel have repaired the locking and isolation equipment;

[0158] The lock release unit is used to, based on the maintenance completion signal, enable the data collection unit to obtain the real-time operating status data of the abnormal device at the time node when the maintenance completion signal is generated, and the data processing unit to perform stability calculation on the real-time operating status data obtained at the time node, thereby obtaining the stability index value corresponding to the time node, and then import the stability index value corresponding to the time node into the multi-time series power grid model through the abnormality analysis unit for abnormality analysis;

[0159] If the analysis result shows that no risk signal is generated, the abnormal device will be released from lock isolation;

[0160] If the analysis result generates a risk signal of the corresponding level, the abnormal device will continue to be locked and isolated. At the same time, the risk warning unit will generate a risk warning notice again according to the level corresponding to the risk signal, and a warning will be issued to relevant personnel again through the dispatch recording phone call;

[0161] At the same time, the operation and maintenance feedback unit and lock release unit of this embodiment allow maintenance personnel to send a maintenance end signal after completing maintenance. The system will re-analyze the stability of the equipment based on real-time data. If the analysis result is normal, the lock isolation of the equipment will be released, thereby improving the flexibility and practicality of the system.

[0162] Example 4

[0163] As the fourth embodiment of the present invention, when this application is specifically implemented, compared with the first, second and third embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above-mentioned first, second and third embodiments.

[0164] This embodiment also acquires power grid equipment analysis data through the data collection unit, and uses the power grid equipment analysis data to perform risk assessment and analysis on the power grid:

[0165] The power grid equipment analysis data includes the number of each device in the power grid and the risk signals of different levels generated by each device during the same target period.

[0166] The risk determination analysis method is as follows:

[0167] SU1, count the total number of devices and mark it as g0;

[0168] SU2. Count the number of devices that generate risk signals and obtain the number of devices with the same level of risk signals;

[0169] The number of devices corresponding to the first-level risk signal is marked as g1;

[0170] The number of devices corresponding to the second-level risk signal is marked as g2;

[0171] The number of devices corresponding to the third-level risk signal is marked as g3;

[0172] The number of devices corresponding to the fourth-level risk signal is marked as g4;

[0173] SU3, through the formula: Calculate the grid framework alert factor H of all equipment in the grid;

[0174] SU4. Compare the grid framework alert coefficients of all devices with the preset risk threshold set F∈[F1, F2, F3]:

[0175] If H≤F1, a first-level warning signal is generated;

[0176] If F1<H≤F2, then the second-level warning signal;

[0177] If F2<H≤F3, then the third-level warning signal;

[0178] If H>F3, then the fourth level warning signal;

[0179] SU5. Generate corresponding alert notices according to the corresponding levels of alert signals through the risk warning unit, and send the alert notices to relevant personnel through the dispatch recording phone.

[0180] A method for temporarily locking equipment risks based on a multi-time-sequence power grid model specifically includes the following steps:

[0181] Collect real-time operating status data from the power grid from monitoring sensors preset in the power grid. The real-time operating status data includes voltage, current, frequency, and temperature parameters of the equipment;

[0182] Perform stability calculation on the real-time running status data and obtain the stability index value of the real-time running status data at the same time node:

[0183] Based on the stability index values ​​obtained from the corresponding real-time operating status data and combined with the preset learning and training rules, a multi-time series power grid model that reflects the status of the power grid at different time points is established;

[0184] Perform an anomaly analysis on the real-time operating status data obtained at the current time node through a multi-time series power grid model. Based on the analysis results, determine whether the equipment is abnormal and generate a risk signal of the corresponding level for the abnormal equipment.

[0185] The corresponding abnormal devices are obtained according to the risk signals of the corresponding levels, and the abnormal devices are locked and isolated through the preset abnormal isolation mechanism.

[0186] A computer device comprises: one or more processors; the processors are used to store one or more programs; when the one or more programs are executed by the one or more processors, a device temporary risk locking method based on a multi-time sequence power grid model is implemented.

[0187] A computer-readable storage medium stores a computer program, which, when executed, implements a device temporary risk locking method based on a multi-time sequence power grid model.

[0188] The present invention has the advantages of real-time monitoring, accurate assessment, anomaly prediction, risk locking, and timely early warning. It can effectively improve the safety and reliability of power grid equipment and provide strong technical support for power grid operation and maintenance.

[0189] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0190] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A temporary risk locking system for equipment based on a multi-time-sequence power grid model, characterized in that: include: A data collection unit is used to collect real-time operating status data of the power grid from monitoring sensors preset in the power grid. The real-time operating status data includes voltage, current, frequency, and temperature parameters of the equipment; The data processing unit is used to perform stability calculation on the real-time operation status data and obtain the stability index value of the real-time operation status data at the same time node: The model building unit is used to build a multi-time series power grid model reflecting the state of the power grid at different time points based on the stability index value obtained by the data processing unit corresponding to the real-time operation status data and in combination with the preset learning and training rules; The abnormality analysis unit is used to perform abnormality analysis on the real-time operating status data obtained at the current time node through a multi-time series power grid model. Based on the analysis results, it determines whether the equipment is abnormal, generates a risk signal of a corresponding level for the abnormal equipment, and transmits the risk signal of a corresponding level generated by the abnormal equipment to the equipment locking unit: The device locking unit is used to obtain the corresponding abnormal device according to the risk signal transmitted by the abnormality analysis unit, and lock and isolate the abnormal device through a preset abnormality isolation mechanism.

2. The equipment temporary risk locking system based on a multi-time-sequence power grid model according to claim 1 is characterized in that: The calculation processing method of the data processing unit is as follows: SA1. Obtain the preset rated voltage, rated current, and rated frequency values ​​of the device, as well as the maximum allowable temperature of the device, and mark them as EU, EI, EP, and Wmax, respectively. SA2. Mark the voltage parameters, current parameters, frequency parameters, and temperature parameters obtained at the same time node in the real-time operating status data as SU, SI, SP, and SW respectively; SA3, through the preset formula: UPC=(SU-EU) / EU*100% IPC=(SI-EI) / EI*100% PPC=(SP-EP) / EP*100% WC=SW-Wmax; The voltage deviation ratio UPC, current deviation ratio IPC, frequency deviation ratio PPC and temperature difference WC are obtained respectively; SA4, through the preset formula: Calculate the stability index value QW corresponding to the real-time running status data at the same time node; Wherein, α1, α2, and α3 are preset weight coefficients, and β is a preset compensation factor.

3. The equipment temporary risk locking system based on a multi-time-sequence power grid model according to claim 1 is characterized in that: The model building unit builds the multi-time-sequence power grid model in the following manner: SS1. Within a plurality of preset specified periods with different time attributes, a number of standard nodes are divided within the corresponding specified periods; SS2. Within multiple specified cycles of the same attribute, obtain real-time operating status data collected on each standard node when the device is operating normally, and extract the stability index value of each standard node after processing by the data processing unit; SS3, screen out multiple stability index values ​​through the discrete degree analysis algorithm, calculate their corresponding average values, and then mark their values ​​as the stability index mean; SS4. Calculate the mean values ​​of the stability indicators corresponding to the specified periods of the same attribute according to the method of step SS3; And select the stability index mean with the minimum and maximum values ​​from all stability index means to form the stability index normal interval [QWmin, QWmax]; QWmin represents the mean of the stability indicator with the smallest median of all stability indicator means; QWmax represents the mean of the stability indicator with the largest median of all stability indicator means; SS5. Within multiple specified cycles of the same attribute, obtain the real-time operating status data collected on each standard node when the equipment is operating abnormally, and extract the stability index value of each standard node after processing by the data processing unit; SS6. Taking a specified period as an example, the interquartile range method is used to screen out the stability indicator means corresponding to the specified period, and the abnormal risk judgment value of the indicator corresponding to the corresponding stability indicator mean is obtained; SS7, and so on, obtain the normal intervals of stability indicators [QWmin, QWmax] and indicator abnormal risk judgment values ​​Z1 and Z2 corresponding to multiple different time attributes, where, in one time attribute, QWmin<QWmax<Z1<Z2; Subsequently, the normal intervals of stability indicators [QWmin, QWmax] and the abnormal risk judgment values ​​Z1 and Z2 of indicators corresponding to each time attribute are trained through preset learning and training rules, and a multi-time series power grid model with different time attribute states is generated.

4. The equipment temporary risk locking system based on a multi-time-sequence power grid model according to claim 3 is characterized in that: The specific method of step SS3 is as follows: Select a specified period and mark the stability index values ​​collected at each standard node as QW j , j = 1, 2, ..., m, m represents the number of standard nodes, j represents the number of standard nodes; Then use the formula Calculate the discrete value L0 of m stability index values, where QW p is the average value of the m stability index values ​​collected; Then the discrete value L0 obtained in the specified period is compared with the preset discrete threshold Ly: If L0>Ly, it means that the discrete degree of each stability index value is large, and then according to |QW j -QW p |Delete the corresponding stability index value QW in descending order j The remaining discrete values ​​L0 are calculated accordingly until L0≤Ly; When L0≤Ly is obtained later, the stability index value QW of the corresponding discrete value L0 is calculated j , and obtain the corresponding stability index values ​​QW j The average of the values ​​is then labeled as the stability indicator mean.

5. The equipment temporary risk locking system based on a multi-time sequence power grid model according to claim 3 is characterized in that: The screening process in step SS6 is as follows: SS61. Sort the stability index values ​​in ascending order to form a sequence table; SS62. In the sequence table, select the first quartile Q1 and the third quartile Q3; SS63, calculate the interquartile range (IQR) by IQR = Q3 - Q1; Among them, the interquartile range IQR reflects the dispersion of the middle 50% of the data; SS64. The indicator abnormal risk judgment values ​​Z1 and Z2 are obtained through the formula: Z1 = Q1 - t*IQR and Z2 = Q3 + t*IQR, where t is a fixed value.

6. The equipment temporary risk locking system based on a multi-time-sequence power grid model according to claim 3 is characterized in that: The abnormality analysis method of the abnormality analysis unit is as follows: SB1. Import the real-time operating status data obtained at the current time node into the data processing unit and perform stability calculation processing. Then, the stability index value corresponding to the current time node is obtained and marked as DQW: SB2. Import the stability index value corresponding to the current time node into the multi-time-sequence power grid model, and the multi-time-sequence power grid model obtains the time attribute of the real-time operating status data corresponding to the current time node; SB3, the multi-time series power grid model obtains the normal range of stability indicators [QWmin, QWmax] and indicator abnormal risk judgment values ​​Z1 and Z2 corresponding to the same time attribute according to the time attribute of the real-time operation status data corresponding to the current time node; SB4. The multi-time-series power grid model compares the stability index value corresponding to the current time node with the normal interval of the stability index [QWmin, QWmax] and the abnormal risk judgment values ​​Z1 and Z2 of the index corresponding to the same time attribute, and obtains the corresponding risk signal.

7. The equipment temporary risk locking system based on a multi-time-sequence power grid model according to claim 6 is characterized in that: In step SB4: If the DQW value is within [QWmin, QWmax], and it includes DQW = QWmin or DQW = QWmax, no risk signal is generated; If DQW<QWmin, a level 1 risk signal is generated; If DQW>QWmax], a secondary risk signal is generated; If QWmax<DQW≤Z1, a level 3 risk signal is generated; If Z1<DQW≤Z2, a level 4 risk signal is generated.

8. The equipment temporary risk locking system based on a multi-time sequence power grid model according to claim 1 is characterized in that: Also includes: The risk warning unit is used to generate risk warning notices based on the corresponding level of risk signals, issue warnings to relevant personnel through dispatching recorded calls, and assign relevant personnel to repair locked and isolated equipment; The operation and maintenance feedback unit is used for the relevant personnel to send a maintenance completion signal through the unit after the relevant personnel have repaired the locking and isolation equipment; The lock release unit is used to enable the data collection unit to obtain the real-time operating status data of the abnormal equipment at the time node when the maintenance end signal is generated according to the maintenance end signal, and the data processing unit performs stability calculation on the real-time operating status data obtained at the time node, and then obtains the stability index value corresponding to the time node, and then imports the stability index value corresponding to the time node into the multi-time series power grid model for abnormality analysis through the abnormality analysis unit, and determines whether to release the lock isolation of the corresponding abnormal equipment according to the analysis results.

9. The equipment temporary risk locking system based on a multi-time-sequence power grid model according to claim 8 is characterized in that: The lock release unit is configured to: If the analysis result shows that no risk signal is generated, the abnormal device will be released from lock isolation; If the analysis result generates a risk signal of the corresponding level, the abnormal equipment will continue to be locked and isolated. At the same time, the risk warning unit will generate a risk warning notice again according to the level corresponding to the risk signal, and a warning will be issued to relevant personnel again through the dispatch recording phone call.

10. A device temporary risk locking method based on a multi-time sequence power grid model, characterized in that: The specific steps include: Collect real-time operating status data from the power grid from monitoring sensors preset in the power grid. The real-time operating status data includes voltage, current, frequency, and temperature parameters of the equipment; Perform stability calculation on the real-time running status data and obtain the stability index value of the real-time running status data at the same time node: Based on the stability index values ​​obtained from the corresponding real-time operating status data and combined with the preset learning and training rules, a multi-time series power grid model that reflects the status of the power grid at different time points is established; Perform an anomaly analysis on the real-time operating status data obtained at the current time node through a multi-time series power grid model. Based on the analysis results, determine whether the equipment is abnormal and generate a risk signal of the corresponding level for the abnormal equipment. The corresponding abnormal devices are obtained according to the risk signals of the corresponding levels, and the abnormal devices are locked and isolated through the preset abnormal isolation mechanism.

11. A computer device, characterized in that: include: one or more processors; The processor is configured to store one or more programs; When the one or more programs are executed by the one or more processors, the method for temporarily locking equipment risks based on a multi-time sequence power grid model as claimed in claim 10 is implemented.

12. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed, a method for temporarily locking equipment risks based on a multi-time sequence power grid model as described in claim 10 is implemented.

Images