Method and system for generating typical operation ticket of substation

Abstract

The present invention discloses a method and system for generating a typical operation ticket for a substation, and specifically relates to the technical field of substations: by monitoring the real-time operating data of equipment and combining trend analysis of historical data, the system can predict the planned operating conditions of the equipment, the comparison between real-time data and predicted data is used to identify abnormal equipment, and a state hysteresis detection algorithm is used to determine whether there is a hysteresis risk; if a risk is detected, a comprehensive analysis of the equipment state and the delay of the operation ticket is performed through fuzzy logic to ensure the accuracy of information when the operation ticket is generated, and if there is no hysteresis information, the operation ticket will be directly submitted for execution; if there is a hysteresis, the system will synchronize the latest operating conditions, evaluate the accuracy of the operation ticket, and decide whether to generate a new operation ticket or suspend the operation based on the evaluation result to ensure the safety and accuracy of the operation.

Description

Technical Field

[0001] The present invention relates to the technical field of substations, and in particular to a method and a system for generating a typical operation ticket of a substation. Background Art

[0002] A typical substation operation ticket is a standardized, written work ticket used to guide operators to perform standardized operations during the operation of the substation. It usually contains a series of operating steps and safety measures to ensure the safety and accuracy of substation equipment during operation, shutdown or switching. A typical operation ticket can cover the closing, pulling, and switching operations of power equipment, and combined with specific operating sequences, operating conditions and precautions, help staff reduce human errors and improve operating efficiency and safety.

[0003] In the prior art, first, an operation procedure library is established based on the equipment operating parameters and operating procedures of the substation, covering the standard operating procedures of various types of equipment. Secondly, the system will automatically identify the current operating conditions and task requirements, such as the status of the equipment, the purpose of the operation, etc., and select the matching operation steps. Then, the generated operation ticket will be optimized and adjusted according to the specific working conditions to ensure the rationality of the operation sequence and safety measures. Finally, the system verifies the generated operation ticket and sends it to the operator for execution after confirmation.

[0004] The prior art has the following deficiencies:

[0005] When the standardized operation process is automatically selected from the operation step library based on the results of the working condition identification, the status of the substation equipment changes in real time. If the system lags behind in the working condition information when generating the operation ticket, for example, a certain device suddenly changes its status (such as from closed to open) after the operation ticket is generated, and the operation ticket fails to reflect the latest status in time, the operator may perform operations based on outdated information. In this case, the judgment basis of the system and the operator deviates, which may lead to dangerous operations. For example, if the operator performs maintenance on live equipment according to the operation ticket, it may cause serious electric shock or short circuit accidents. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for generating a typical operation ticket of a substation, so as to solve the shortcomings of the background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for generating a typical operation ticket of a substation, comprising the following steps:

[0008] S1: Monitoring, obtaining real-time operating data of all equipment related to the operation ticket in the substation, and linking with the monitoring system. The real-time operating data includes real-time operating status data and real-time operation data of the equipment;

[0009] S2: Obtain historical operating condition data of equipment related to the operation ticket in several different time periods from historical data, perform trend analysis on the historical operating condition data, and predict planned operating condition data of the equipment related to the operation ticket, wherein the planned operating condition data is predicted operating status data and predicted operation data of the equipment;

[0010] S3: Compare and analyze the real-time operating data and predicted operation data of the equipment related to the operation ticket, and determine the abnormal equipment with inconsistent operating status based on the analysis results. For abnormal equipment, use the state hysteresis detection algorithm to determine the delay between the equipment state change and the generation of the operation ticket. If the delay is large, there is a risk of information lag;

[0011] S4: For abnormal equipment with hysteresis risk, fuzzy logic is used to comprehensively analyze the consistency of the abnormal equipment’s operating status and the delay between generating the operation ticket to determine whether there is hysteresis information when generating the operation ticket; if there is no hysteresis information, the operation ticket is submitted to the operator for execution, and the corresponding operation instructions are issued.

[0012] Preferably, in S3, the real-time operating data and predicted operating data of all equipment related to the operation ticket are compared and analyzed to generate the equipment state change rate deviation index, and the method for obtaining the equipment state change rate deviation index is:

[0013] At the initial moment , generate a set of N random particles to represent the initial state of the device, the initial state of the particles is the prior distribution of the slave device state The sampling is obtained, ,in represents the i-th particle, and is the initial weight of each particle Set to be equal, ,in Represents the weight of the i-th particle; predicts the next moment of each particle based on the state transition model of the device The state is expressed as: ; In the formula, is the i-th particle at time The predicted state of is the device state transition model, which represents the transition from time To time The rate of state change, is the system noise, at time , based on the real-time operating data of the equipment The state of each particle is observed and the weight is updated. The expression is: ;in, is the observation function, which means the particle state The observed values ​​obtained, For the observation noise, we assume it comes from a Gaussian distribution ; Update the particle weights according to the observed values, ;in is the likelihood of the particle, i.e. the observed value In particle state The probability of: ; To observe the variance of the noise, the real-time state comprehensive change rate is calculated based on the state change rate of all particles. , the expression is: ; Calculate the equipment state change rate deviation index, the expression is: ; In the formula, The preset deviation value is for the equipment state change rate under normal conditions in historical data, and HG is the equipment state change rate deviation index.

[0014] Preferably, the acquired equipment state change rate deviation index is compared with a preset equipment state change rate deviation index reference threshold. If the equipment state change rate deviation index is greater than or equal to the preset equipment state change rate deviation index reference threshold, the real-time operating data and predicted operating data of the equipment related to the operation ticket are inconsistent, and it is marked as an abnormal device; if the equipment state change rate deviation index is less than the preset equipment state change rate deviation index reference threshold, the real-time operating data and predicted operating data of the equipment related to the operation ticket are consistent, and it is marked as a normal device.

[0015] Preferably, in S3, the delay between the equipment state change and the generation of the operation ticket is determined by the state hysteresis detection algorithm and the state hysteresis time abnormality index is generated. The state hysteresis time abnormality index is obtained as follows:

[0016] The delay time between the equipment status change and the generation of the operation ticket is marked as , and establish a historical lag time data set to construct a priori distribution. After the current operation ticket is generated, record the delay time of the actual state change of the equipment and calculate the priori distribution of the lag time , the expression is: ; μ is the mean of the lag time, representing the typical lag time of the device, is the variance of the lag time, and the current device lag time is is the lag time observed in real time, and the expression is: ; In the formula, The variance of the observed noise is used to calculate the posterior probability that the current lag time of the device is abnormal through Bayes’ theorem. , the expression is: ; In the formula, is the marginal probability constant of the observed data; the state lag time anomaly index is calculated, and the expression is: ; In the formula, is the state lag time anomaly index.

[0017] Preferably, the acquired state lag time anomaly index is compared with a preset reference threshold of the state lag time anomaly index. If the state lag time anomaly index is greater than or equal to the preset reference threshold of the state lag time anomaly index, it means that the delay between the equipment state change and the generation of the operation ticket is large, and there is a risk of information lag; if the state lag time anomaly index is less than the preset reference threshold of the state lag time anomaly index, it means that the delay between the equipment state change and the generation of the operation ticket is small, and there is no risk of information lag.

[0018] Preferably, in S4, for abnormal equipment with a risk of hysteresis, a comprehensive analysis is performed on the consistency of the operation status of the abnormal equipment and the delay between generating the operation ticket through fuzzy logic to determine whether there is hysteresis information when generating the operation ticket;

[0019] The equipment state change rate deviation index HG and the state lag time abnormality index KM are used as the input items of fuzzy logic, and the real-time value K of the information when generating the operation ticket is used as the output item;

[0020] Divide HG, KM and K into different fuzzy sets;

[0021] According to different combinations of input items HG and KM, fuzzy rules are formulated;

[0022] The actual input item state change rate deviation index HG and state lag time abnormality index KM are converted into fuzzy values ​​through membership function;

[0023] Substitute the fuzzified input items HG and KM into the corresponding rules, calculate the membership degree of the output item K, and obtain the fuzziness degree of each K through rule matching;

[0024] Convert the fuzzy result into a specific value K;

[0025] The real-time nature of the information when generating the operation ticket is determined based on the defuzzified K value. If the K value is less than the preset real-time value reference threshold, it indicates that there is lagging information.

[0026] Preferably, if there is lagging information, the real-time working status of the equipment is resynchronized, and the accuracy of the information when the operation ticket is generated within a fixed time period is predicted. If the accuracy is high, the operation ticket is regenerated. If the accuracy is low, the execution of the current operation ticket is suspended, and an alarm is immediately issued to the operator, specifically:

[0027] If there is lagging information, the real-time operating status of the equipment is resynchronized, and the accuracy of the information when the operation ticket is generated within a fixed time period is predicted. The real-time value K of the information when the operation ticket is generated within a fixed time period is collected, and the corresponding data set is established. The mean and standard deviation of the data set are calculated. After analysis, the accuracy of the information when the operation ticket is generated within a fixed time period is determined.

[0028] Preferably, if the mean of the real-time values ​​in the data set is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, the information accuracy when generating the operation ticket is high and the fluctuation is small, and the information is stable, the operation ticket is regenerated and submitted for execution;

[0029] If the mean of the real-time values ​​is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the real-time values, although the accuracy of the information is high, the fluctuation is large and there is instability. Further confirmation of the real-time working conditions is required and the execution is temporarily not performed;

[0030] If the mean of the real-time value is less than the reference threshold of the mean of the real-time value, and the standard deviation of the real-time value is greater than or equal to the reference threshold of the standard deviation of the real-time value, the information accuracy is low and the fluctuation is large, and the real-time working condition is unstable, the execution of the current operation ticket is suspended, and an alarm is immediately issued to the operator;

[0031] If the mean of the real-time values ​​is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, the information accuracy is low but the fluctuation is small, and the execution of the operation ticket is suspended.

[0032] The present invention also provides a generation system of a typical operation ticket of a substation, including a real-time monitoring module, a historical data and trend analysis module, a data comparison and anomaly detection module and a fuzzy logic analysis module;

[0033] Real-time monitoring module: monitors and obtains the real-time working condition data of all equipment related to the operation ticket in the substation, and links with the monitoring system. The real-time working condition data includes the real-time operating status data and real-time operation data of the equipment;

[0034] Historical data and trend analysis module: obtain historical operating data of equipment related to the operation ticket in several different time periods from historical data, perform trend analysis on the historical operating data, and predict the planned operating data of the equipment related to the operation ticket. The planned operating data is the predicted operating status data and predicted operation data of the equipment;

[0035] Data comparison and anomaly detection module: compares and analyzes the real-time operating data and predicted operation data of the equipment related to the operation ticket, and determines the abnormal equipment with inconsistent operating status based on the analysis results. For abnormal equipment, the delay between the equipment status change and the generation of the operation ticket is determined through the state lag detection algorithm. If the delay is large, there is a risk of information lag;

[0036] Fuzzy logic analysis module: For abnormal equipment with hysteresis risk, fuzzy logic is used to comprehensively analyze the consistency of the abnormal equipment's operating status and the delay between generating the operation ticket to determine whether there is hysteresis information when generating the operation ticket; if there is no hysteresis information, the operation ticket is submitted to the operator for execution, and the corresponding operation instructions are issued.

[0037] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0038] 1. The present invention predicts the planned operating conditions of the equipment by real-time monitoring of the equipment's operating data and combining it with trend analysis of historical data. When the real-time data is inconsistent with the predicted data, the system uses a state hysteresis detection algorithm to determine whether there is a hysteresis risk, and uses fuzzy logic to conduct a comprehensive analysis of the equipment state consistency and delay to ensure the accuracy of information when generating an operation ticket. If there is no hysteresis risk, the operation ticket will be submitted for execution in a timely manner; if there is a hysteresis risk, the equipment state will be resynchronized and the real-time performance of the operation ticket will be evaluated to ensure that there will be no misoperation when hysteresis information exists.

[0039] 2. The present invention achieves more accurate operation ticket generation and monitoring by introducing the equipment state change rate deviation index and the state lag time abnormality index, which greatly reduces the risk of misoperation caused by operating condition lag, especially when the equipment state changes frequently. Through fuzzy logic analysis, defuzzification processing and accuracy prediction of data sets, the system can dynamically adjust the execution time of the operation ticket, thereby improving operational safety and stability, reducing the occurrence of human errors, and further ensuring the stable operation of substation equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 The present invention is a flow chart of the method.

[0042] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example 1, please refer to Figure 1 As shown, the method for generating a typical substation operation ticket in this embodiment includes the following steps:

[0045] S1: Monitoring, obtaining real-time operating data of all equipment related to the operation ticket in the substation, and linking with the monitoring system. The real-time operating data includes real-time operating status data and real-time operation data of the equipment;

[0046] S2: Obtain historical operating condition data of equipment related to the operation ticket in several different time periods from historical data, perform trend analysis on the historical operating condition data, and predict planned operating condition data of the equipment related to the operation ticket, wherein the planned operating condition data is predicted operating status data and predicted operation data of the equipment;

[0047] S3: Compare and analyze the real-time operating data and predicted operation data of the equipment related to the operation ticket, and determine the abnormal equipment with inconsistent operating status based on the analysis results. For abnormal equipment, use the state hysteresis detection algorithm to determine the delay between the equipment state change and the generation of the operation ticket. If the delay is large, there is a risk of information lag;

[0048] S4: For abnormal equipment with hysteresis risk, fuzzy logic is used to comprehensively analyze the consistency of the abnormal equipment’s operating status and the delay between generating the operation ticket to determine whether there is hysteresis information when generating the operation ticket; if there is no hysteresis information, the operation ticket is submitted to the operator for execution, and the corresponding operation instructions are issued.

[0049] Among them, in S1, the real-time working condition data of all equipment related to the operation ticket in the substation is monitored and acquired, and linked with the monitoring system. The real-time working condition data includes the real-time running status data and real-time operation data of the equipment.

[0050] Monitoring, obtaining real-time operating data of all equipment related to the operation ticket in the substation, including all substation equipment related to the operation ticket, including but not limited to: Circuit breaker (switch): used to control the opening and closing of the circuit and monitor its closing or disconnecting status. Isolating switch: monitor its opening or closing status to ensure the reliability of circuit segmentation isolation. Transformer: including monitoring of real-time parameters such as operating status, current, voltage, etc. to determine whether it is in normal working condition. Bus: monitor operating status such as voltage, current, load, etc. to ensure the health of the bus. Capacitors, mutual inductors: The real-time operating data of these devices can be used to analyze power quality and other conditions. Protection device: used to detect faults and the action of protection equipment, including whether tripping, overload, short circuit, etc. occurs. Grounding switch: monitors the grounding status to ensure the safety of maintenance and repair operations. Auxiliary equipment: such as the monitoring system itself, communication equipment, environmental sensors, etc., also need to ensure their reliability through real-time status data.

[0051] The real-time operating data related to the operation ticket refers to various types of information reflecting the current operating status and operation status of the substation equipment, usually including the following main data types:

[0052] For circuit breakers, disconnectors, earthing switches and other equipment, monitor whether they are currently in the closed state (closed) or disconnected state to ensure that the circuit connection of the equipment is as expected. Monitor the electrical parameters such as current, voltage, power, frequency and other electrical parameters of all equipment. These data reflect the actual load, power supply and health status of the equipment. For example: Voltage: indicates whether the equipment is operating within the normal voltage range. Current: can be used to detect whether the equipment is overloaded or unloaded. Power: used to analyze the load of the equipment. Environmental data such as temperature and humidity: Changes in the temperature and humidity of the environment in which the equipment is located may affect the working state of the equipment, and these data also need to be monitored in real time. Monitor the action status of the relay protection device to determine whether the equipment is affected by the protection action, such as equipment tripping or starting fault protection. Real-time monitoring of whether the equipment has received operation instructions such as opening and closing, disconnecting or closing the disconnector, and recording its response to confirm whether the operation is performed correctly.

[0053] The real-time monitoring system of the substation (such as the SCADA system, Supervisory Control and Data Acquisition) is the core system for collecting, transmitting, processing and displaying the operating data of the power grid and substation equipment. When generating an operation ticket, it must be linked with the monitoring system to ensure that the acquired equipment condition data is the latest and most complete. The specific methods and functions of the linkage are as follows:

[0054] The SCADA system collects data from various devices in the substation in real time through field sensors, intelligent electrical equipment, protection devices, etc., and transmits it to the central control room or data processing system through the communication network. The operation ticket system is connected to the SCADA system through an interface to obtain real-time operating data of all relevant equipment. The SCADA system not only collects equipment data, but also can remotely operate the equipment, such as executing disconnect or close commands. The operation ticket system can realize real-time monitoring of remote equipment operation steps by linking with the SCADA system.

[0055] S2: Obtain historical operating condition data of equipment related to the operation ticket in several different time periods from historical data, perform trend analysis on the historical operating condition data, and predict planned operating condition data of the equipment related to the operation ticket, wherein the planned operating condition data is the predicted operating status data and predicted operation data of the equipment.

[0056] First, extract the historical operating data of the equipment related to the operation ticket from the substation monitoring system (such as the SCADA system). These data cover the operating status and operation records of the equipment in different time periods. It is usually necessary to obtain the recent historical data of the equipment, such as the past 24 hours, the past week, the past month, etc. These data can reflect the latest operating trends and load changes of the equipment. For some equipment, it is also necessary to extract longer historical data (such as half a year or a year) to analyze its long-term operating status and health status. Including equipment operating status: such as the closing / disconnecting history of circuit breakers, transformers, switches, equipment tripping records, and equipment load fluctuations. Electrical parameters: Obtain historical current, voltage, power, frequency and other parameter change data, which helps to determine whether the equipment has experienced abnormal conditions such as overload and low voltage. Operation history record: record all operation commands executed by the equipment, the operation response of the equipment (such as operation failure, timeout, etc.), especially the key opening and closing, switching operations. Fault and alarm records: record whether the equipment has experienced abnormal conditions such as faults and alarms, and analyze the frequency and cause of faults and the impact on the equipment status.

[0057] After extracting historical operating data, data cleaning and preprocessing are required to ensure data accuracy and completeness. If the device generates extreme data due to sensor failure or external factors (for example, abnormal instantaneous voltage increase), these data that do not conform to the actual situation need to be cleared. Data from different devices may come from different systems and the time format may be different. The timestamps need to be unified into a standard format. Unit unification and normalization of different parameters (such as voltage, current, etc.) are performed to facilitate subsequent trend analysis.

[0058] By performing trend analysis on historical operating data, we can discover the operating rules of the equipment, identify potential problems, and predict possible future operating conditions, including: using the sliding average method to smooth data, remove short-term fluctuations, and analyze the medium- and long-term trends of the equipment. For example, analyze the rising or falling trend of transformer load in the past year. The load or status of some equipment may be affected by seasons or time periods (such as higher loads in summer), and seasonal patterns can be identified through time series analysis.

[0059] Through trend analysis and the rules of historical data, the possible operating conditions of the equipment in the future are predicted, and the planned operating condition data of the equipment is generated. These predicted operating condition data are used as a reference when generating operation tickets to ensure that the operating steps are adapted to the future equipment status. Based on the trend of historical load data, the future load conditions of the equipment are predicted. For example, the load changes of the transformer in the next 24 hours are analyzed to avoid overload operation. Based on the equipment's past failure frequency, service life, and maintenance records, the health status of the equipment in the future is predicted. If the equipment failure frequency increases, the planned operating condition may need to consider equipment shutdown maintenance. If the equipment has been in a relatively stable operating state in the past period of time (such as being in a closed state for a long time), it can be predicted that its state will remain stable in the future, reducing unnecessary operations.

[0060] Based on the historical operation records of the equipment, possible operation requirements are predicted. For example, if the equipment frequently performs load switching operations in a specific time period, the system can predict that similar operations may be required in the same time period in the future. Based on the operation history of the equipment (such as the success rate of opening and closing, response time, etc.), the success rate and possible delays of its future operations are predicted, and the operation sequence and time schedule in the operation ticket are adjusted in advance.

[0061] Based on the trend analysis results, the planned operating condition data is generated, including the following two parts:

[0062] Predicted operating status data: reflects the possible status of the equipment in a certain period of time in the future. For example, it is predicted that a circuit breaker will remain in the closed state in the next 24 hours, or the load of a transformer will reach 90% in the future.

[0063] Predicted operational data: Contains possible future operational requirements and responses. For example, it is expected that a disconnector will need to be switched at a certain point in time, or that a device failure may trigger a protection trip.

[0064] S3: Compare and analyze the real-time operating data and predicted operation data of the equipment related to the operation ticket, and determine the abnormal equipment with inconsistent operating status based on the analysis results. For abnormal equipment, use the state lag detection algorithm to determine the delay between the equipment status change and the generation of the operation ticket. If the delay is large, there is a risk of information lag.

[0065] The equipment state change rate deviation index is generated by comparing and analyzing the real-time working condition data and predicted operation data of all equipment related to the operation ticket. The method for obtaining the equipment state change rate deviation index is as follows:

[0066] At the initial moment , generate a set of N random particles to represent the initial state of the device, the initial state of the particles is the prior distribution of the slave device state The sampling is obtained, ,in represents the i-th particle, and is the initial weight of each particle Set to be equal, ,in represents the weight of the ith particle.

[0067] According to the state transition model of the device, predict the next moment of each particle The state is expressed as: ; In the formula, is the i-th particle at time The predicted state of is the device state transition model, which represents the transition from time To time The rate of state change, is the system noise, simulating the uncertainty of the device state.

[0068] At the moment , based on the real-time operating data of the equipment The state of each particle is observed and the weight is updated. The expression is: ;in, is the observation function, which means the particle state The observed values ​​obtained, For the observation noise, we assume it comes from a Gaussian distribution ; Update the particle weights according to the observed values, ;in is the likelihood of the particle, i.e. the observed value In particle state The probability of . It is usually assumed that the observation noise is Gaussian distributed, so: ; To observe the variance of noise and control the volatility of observed data, the real-time state comprehensive change rate is calculated based on the state change rate of all particles. , the expression is: ; Calculate the equipment state change rate deviation index, the expression is: ; In the formula, The preset deviation value is for the equipment state change rate under normal conditions in historical data, and HG is the equipment state change rate deviation index.

[0069] The acquired equipment state change rate deviation index is compared with the preset equipment state change rate deviation index reference threshold. If the equipment state change rate deviation index is greater than or equal to the preset equipment state change rate deviation index reference threshold, the real-time operating data and predicted operating data of the equipment related to the operation ticket are inconsistent, and it is marked as an abnormal device; if the equipment state change rate deviation index is less than the preset equipment state change rate deviation index reference threshold, the real-time operating data and predicted operating data of the equipment related to the operation ticket are consistent, and it is marked as a normal device.

[0070] For abnormal equipment, the delay between the equipment status change and the generation of the operation ticket is determined by the state hysteresis detection algorithm. If the delay is large, there is a risk of information lag, specifically:

[0071] The state hysteresis detection algorithm is used to determine the delay between the equipment state change and the generation of the operation ticket and generate the state hysteresis time anomaly index. The state hysteresis time anomaly index is obtained as follows:

[0072] The delay time between the equipment status change and the generation of the operation ticket is marked as , and establish a historical lag time data set to construct a priori distribution. After the current operation ticket is generated, record the delay time of the actual state change of the equipment and calculate the priori distribution of the lag time , the expression is: ; μ is the mean of the lag time, representing the typical lag time of the device, The variance of the lag time reflects the fluctuation of the lag time. is the lag time observed in real time, and the expression is: ; In the formula, is the variance of the observed noise, reflecting the measurement error or system noise. Using Bayesian theorem, the posterior probability that the current lag time of the device is abnormal is calculated. , the expression is: ; In the formula, is the marginal probability constant of the observed data; the state lag time anomaly index is calculated, and the expression is: ; In the formula, is the state lag time anomaly index.

[0073] The obtained status lag time anomaly index is compared with the preset reference threshold of the status lag time anomaly index. If the status lag time anomaly index is greater than or equal to the preset reference threshold of the status lag time anomaly index, it means that the delay between the equipment status change and the generation of the operation ticket is large, and there is a risk of information lag; if the status lag time anomaly index is less than the preset reference threshold of the status lag time anomaly index, it means that the delay between the equipment status change and the generation of the operation ticket is small, and there is no risk of information lag.

[0074] S4: For abnormal equipment with hysteresis risk, fuzzy logic is used to comprehensively analyze the consistency of the abnormal equipment’s operating status and the delay between generating the operation ticket to determine whether there is hysteresis information when generating the operation ticket; if there is no hysteresis information, the operation ticket is submitted to the operator for execution, and the corresponding operation instructions are issued.

[0075] The equipment state change rate deviation index HG and the state lag time abnormality index KM are used as the input items of fuzzy logic, and the real-time value K of the information when generating the operation ticket is used as the output item;

[0076] Divide HG into different fuzzy sets, for example: Low: almost no deviation, Medium: the deviation is within the acceptable range, High: the deviation is very significant;

[0077] Divide KM into different fuzzy sets, for example: Normal: no significant abnormality in lag time, Moderate: some deviation in lag time, Severe: serious deviation in lag time. Divide K into different fuzzy sets, for example: Real-time: very timely information, no lag; Moderate Real-time: a small amount of information delay, no lag; Non-real-time: information lag.

[0078] According to different combinations of input items HG and KM, fuzzy rules are formulated to output the evaluation results of the real-time performance of the operation ticket information. Rule number State change rate deviation index (HG) State lag time abnormality index (KM) Real-time of information when generating operation ticket (K); Rule 1: HG is small (Low) KM is normal (Normal) K Real-time (Real-time); Rule 2: HG is small (Low) KM is moderately abnormal (Moderate) K Moderate real-time (Moderate Real-time); Rule 3: HG is small (Low) KM is severely abnormal (Severe) K Non-real-time (Non-real-time); Rule 4: HG is medium (Medium) KM is normal (Normal) K Moderate real-time (Moderate Real-time); Rule 5: HG is medium (Medium) KM is moderately abnormal (Moderate) K Non-real-time (Non-real-time); Rule 6: HG is medium (Medium) KM is severely abnormal (Severe) K Non-real-time (Non-real-time); Rule 7: HG is large (High) KM is normal (Normal) K Moderate real-time (Moderate Real-time); Rule 8: HG is large (High) KM moderate abnormality (Moderate) K non-real-time (Non-real-time); Rule 9: HG high (High) KM severe abnormality (Severe) K non-real-time (Non-real-time).

[0079] The actual input item state change rate deviation index (HG) and state lag time abnormality index (KM) are converted into fuzzy values ​​through membership function.

[0080] Substitute the fuzzified input items HG and KM into the corresponding rules and calculate the membership degree of the output item K. The fuzziness degree of each K is obtained through rule matching.

[0081] The fuzzification result is converted into a specific value K (the real-time nature of information when generating an operation ticket). Commonly used defuzzification methods include the Centroid Method.

[0082] The real-time nature of the information when generating the operation ticket is determined based on the defuzzified K value. If the K value is less than the preset real-time value reference threshold, it indicates that there is lagging information. The system can issue an alarm or automatically adjust the operation ticket generation strategy to avoid potential risks.

[0083] If the analysis confirms that there is no lag information, the system will submit the generated operation ticket to the operator for execution. Each step of the operation ticket has been verified to ensure that it is consistent with the real-time working conditions of the equipment to avoid misoperation or safety hazards. The system also issues corresponding operation instructions to guide the operator to perform the operation safely and accurately according to the instructions in the operation ticket, ensuring that the operation of the substation equipment remains normal and stable.

[0084] Furthermore, if there is lagging information, the real-time operating status of the equipment is resynchronized, and the accuracy of the information when generating an operation ticket within a fixed time period is predicted. If the accuracy is high, the operation ticket is regenerated. If the accuracy is low, the execution of the current operation ticket is suspended and an alarm is immediately issued to the operator.

[0085] If there is lagging information, the real-time operating status of the equipment is resynchronized, and the accuracy of the information when the operation ticket is generated within a fixed time period is predicted. The real-time value K of the information when the operation ticket is generated within a fixed time period is collected, and the corresponding data set is established. The mean and standard deviation of the data set are calculated. After analysis, the accuracy of the information when the operation ticket is generated within a fixed time period is determined.

[0086] If the mean of the real-time values ​​in the data set is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, the information accuracy when generating the operation ticket is high and the fluctuation is small, and the information is stable, the operation ticket is regenerated and submitted for execution;

[0087] If the mean of the real-time values ​​is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the real-time values, although the accuracy of the information is high, the fluctuation is large and there is instability. Further confirmation of the real-time working conditions is required and the execution is temporarily not performed;

[0088] If the mean of the real-time value is less than the reference threshold of the mean of the real-time value, and the standard deviation of the real-time value is greater than or equal to the reference threshold of the standard deviation of the real-time value, the information accuracy is low and the fluctuation is large, and the real-time working condition is unstable, the execution of the current operation ticket is suspended, and an alarm is immediately issued to the operator;

[0089] If the mean of the real-time values ​​is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, the information accuracy is low but the fluctuation is small, indicating that the information deviation may be a persistent problem. The execution of the operation ticket should be suspended, and the reasons for the delay should be further analyzed to ensure that the data is synchronized before performing the operation.

[0090] In this embodiment, the monitoring system acquires the operating data of the substation equipment in real time, and then predicts the planned operating conditions of the equipment through trend analysis of historical data. Next, the real-time data is compared with the predicted data to identify abnormal equipment with inconsistent operating status, and the delay between the equipment status change and the generation of the operation ticket is determined by the state hysteresis detection algorithm. If the delay is large, there is a risk of information hysteresis. For the hysteresis risk, fuzzy logic is used to analyze the delay between the equipment status and the operation ticket to determine whether there is hysteresis information. If there is no hysteresis information, the operation ticket is submitted to the operator for execution; if there is hysteresis information, the system will resynchronize the equipment status and evaluate the accuracy of the operation ticket. If the accuracy is high, the operation ticket will be regenerated; if the accuracy is low, the operation will be suspended and an alarm will be issued.

[0091] Example 2, please refer to Figure 2 As shown, the generation system of the typical operation ticket of the substation described in this embodiment includes a real-time monitoring module, a historical data and trend analysis module, a data comparison and anomaly detection module and a fuzzy logic analysis module;

[0092] Real-time monitoring module: monitors and obtains the real-time working condition data of all equipment related to the operation ticket in the substation, and links with the monitoring system. The real-time working condition data includes the real-time operating status data and real-time operation data of the equipment;

[0093] Historical data and trend analysis module: obtain historical operating data of equipment related to the operation ticket in several different time periods from historical data, perform trend analysis on the historical operating data, and predict the planned operating data of the equipment related to the operation ticket. The planned operating data is the predicted operating status data and predicted operation data of the equipment;

[0094] Data comparison and anomaly detection module: compares and analyzes the real-time operating data and predicted operation data of the equipment related to the operation ticket, and determines the abnormal equipment with inconsistent operating status based on the analysis results. For abnormal equipment, the delay between the equipment status change and the generation of the operation ticket is determined through the state lag detection algorithm. If the delay is large, there is a risk of information lag;

[0095] Fuzzy logic analysis module: For abnormal equipment with hysteresis risk, fuzzy logic is used to comprehensively analyze the consistency of the abnormal equipment's operating status and the delay between generating the operation ticket to determine whether there is hysteresis information when generating the operation ticket; if there is no hysteresis information, the operation ticket is submitted to the operator for execution, and the corresponding operation instructions are issued.

[0096] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0097] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0098] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0099] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0100] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0101] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for generating a typical substation operation ticket, characterized in that: The following steps are involved: S1: Monitoring, obtaining real-time operating data of all equipment related to the operation ticket in the substation, and linking with the monitoring system. The real-time operating data includes real-time operating status data and real-time operation data of the equipment; S2: Obtain historical operating condition data of equipment related to the operation ticket in several different time periods from historical data, perform trend analysis on the historical operating condition data, and predict planned operating condition data of the equipment related to the operation ticket, wherein the planned operating condition data is predicted operating status data and predicted operation data of the equipment; S3: Compare and analyze the real-time operating data and predicted operation data of the equipment related to the operation ticket, and determine the abnormal equipment with inconsistent operating status based on the analysis results. For abnormal equipment, use the state hysteresis detection algorithm to determine the delay between the equipment state change and the generation of the operation ticket. If the delay is large, there is a risk of information lag; The step S3 includes: determining the delay between the equipment state change and the generation of the operation ticket through the state hysteresis detection algorithm and generating a state hysteresis time abnormality index. The state hysteresis time abnormality index is obtained as follows: The delay time between the equipment status change and the generation of the operation ticket is marked as , and establish a historical lag time data set to construct a priori distribution. After the current operation ticket is generated, record the delay time of the actual state change of the equipment and calculate the priori distribution of the lag time , the expression is: μ is the mean of the lag time, representing the typical lag time of the device. is the variance of the lag time, and the current device lag time is is the lag time observed in real time, and the expression is: In the formula, The variance of the observed noise is used to calculate the posterior probability that the current lag time of the device is abnormal through Bayes’ theorem. , the expression is: In the formula, is the marginal probability constant of the observed data; the state lag time anomaly index is calculated, and the expression is: ; In the formula, is the state lag time anomaly index; S4: For abnormal equipment with hysteresis risk, a comprehensive analysis is performed on the consistency of the abnormal equipment's operating status and the delay between generating the operation ticket through fuzzy logic to determine whether there is hysteresis information when generating the operation ticket; if there is no hysteresis information, the operation ticket is submitted to the operator for execution, and the corresponding operation instruction is issued; The step S4 includes: using the equipment state change rate deviation index HG and the state lag time abnormality index KM as input items of fuzzy logic, and using the real-time value K of the information when generating the operation ticket as the output item; Divide HG, KM and K into different fuzzy sets; According to different combinations of input items HG and KM, fuzzy rules are formulated; The actual input item state change rate deviation index HG and state lag time abnormality index KM are converted into fuzzy values ​​through membership function; Substitute the fuzzified input items HG and KM into the corresponding rules, calculate the membership degree of the output item K, and obtain the fuzziness degree of each K through rule matching; Convert the fuzzy result into a specific value K; The real-time nature of the information when generating the operation ticket is determined based on the defuzzified K value. If the K value is less than the preset real-time value reference threshold, it indicates that there is lagging information.

2. The method for generating a typical substation operation ticket according to claim 1, characterized in that: In S3, the real-time working condition data and predicted operation data of all equipment related to the operation ticket are compared and analyzed to generate the equipment state change rate deviation index. The method for obtaining the equipment state change rate deviation index is: At the initial moment , generate a set of N random particles to represent the initial state of the device, the initial state of the particles is the prior distribution of the slave device state The sampling is obtained, ,in represents the i-th particle, and is the initial weight of each particle Set to be equal, ,in Represents the weight of the i-th particle; predicts the next moment of each particle based on the state transition model of the device The state is expressed as: ; In the formula, is the i-th particle at time The predicted state of is the device state transition model, which represents the transition from time To time The rate of state change, is the system noise, at time , based on the real-time operating data of the equipment The state of each particle is observed and the weight is updated. The expression is: ;in, is the observation function, which means the particle state The observed values ​​obtained, For the observation noise, we assume it comes from a Gaussian distribution ; Update the particle weights according to the observed values, ;in is the likelihood of the particle, i.e. the observed value In particle state The probability of: To observe the variance of the noise, the real-time state comprehensive change rate is calculated based on the state change rate of all particles. , the expression is: ; Calculate the equipment state change rate deviation index, the expression is: ; In the formula, The preset deviation value is for the equipment state change rate under normal conditions in historical data, and HG is the equipment state change rate deviation index.

3. The method for generating a typical substation operation ticket according to claim 2, characterized in that: The acquired equipment state change rate deviation index is compared with the preset equipment state change rate deviation index reference threshold. If the equipment state change rate deviation index is greater than or equal to the preset equipment state change rate deviation index reference threshold, the real-time operating data and predicted operation data of the equipment related to the operation ticket are inconsistent, and it is marked as an abnormal equipment. If the equipment state change rate deviation index is less than the preset equipment state change rate deviation index reference threshold, the real-time operating data of the equipment related to the operation ticket is consistent with the predicted operation data, and it is marked as a normal equipment.

4. The method for generating a typical substation operation ticket according to claim 1, characterized in that: The obtained status lag time anomaly index is compared with the preset reference threshold of the status lag time anomaly index. If the status lag time anomaly index is greater than or equal to the preset reference threshold of the status lag time anomaly index, it means that the delay between the equipment status change and the generation of the operation ticket is large, and there is a risk of information lag; if the status lag time anomaly index is less than the preset reference threshold of the status lag time anomaly index, it means that the delay between the equipment status change and the generation of the operation ticket is small, and there is no risk of information lag.

5. The method for generating a typical substation operation ticket according to claim 1, characterized in that: If there is lagging information, the real-time working status of the equipment is resynchronized, and the accuracy of the information when the operation ticket is generated within a fixed time period is predicted. If the accuracy is high, the operation ticket is regenerated. If the accuracy is low, the execution of the current operation ticket is suspended and an alarm is immediately issued to the operator. Specifically: If there is lagging information, the real-time operating status of the equipment is resynchronized, and the accuracy of the information when the operation ticket is generated within a fixed time period is predicted. The real-time value K of the information when the operation ticket is generated within a fixed time period is collected, and the corresponding data set is established. The mean and standard deviation of the data set are calculated. After analysis, the accuracy of the information when the operation ticket is generated within a fixed time period is determined.

6. The method for generating a typical substation operation ticket according to claim 5, characterized in that: If the mean of the real-time values ​​in the data set is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, the information accuracy when generating the operation ticket is high and the fluctuation is small, and the information is stable, the operation ticket is regenerated and submitted for execution; If the mean of the real-time values ​​is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the real-time values, although the accuracy of the information is high, the fluctuation is large and there is instability. Further confirmation of the real-time working conditions is required and the execution is temporarily not performed; If the mean of the real-time value is less than the reference threshold of the mean of the real-time value, and the standard deviation of the real-time value is greater than or equal to the reference threshold of the standard deviation of the real-time value, the information accuracy is low and the fluctuation is large, and the real-time working condition is unstable, the execution of the current operation ticket is suspended, and an alarm is immediately issued to the operator; If the mean of the real-time values ​​is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values ​​is less than the reference threshold of the standard deviation of the real-time values, the information accuracy is low but the fluctuation is small, and the execution of the operation ticket is suspended.

7. A system for generating a typical operation ticket for a substation, used to implement the method for generating a typical operation ticket for a substation according to any one of claims 1 to 6, characterized in that: It includes real-time monitoring module, historical data and trend analysis module, data comparison and anomaly detection module and fuzzy logic analysis module; Real-time monitoring module: monitors and obtains the real-time working condition data of all equipment related to the operation ticket in the substation, and links with the monitoring system. The real-time working condition data includes the real-time operating status data and real-time operation data of the equipment; Historical data and trend analysis module: obtain historical operating data of equipment related to the operation ticket in several different time periods from historical data, perform trend analysis on the historical operating data, and predict the planned operating data of the equipment related to the operation ticket. The planned operating data is the predicted operating status data and predicted operation data of the equipment; Data comparison and anomaly detection module: compares and analyzes the real-time operating data and predicted operation data of the equipment related to the operation ticket, and determines the abnormal equipment with inconsistent operating status based on the analysis results. For abnormal equipment, the delay between the equipment status change and the generation of the operation ticket is determined through the state lag detection algorithm. If the delay is large, there is a risk of information lag; Fuzzy logic analysis module: For abnormal equipment with hysteresis risk, fuzzy logic is used to comprehensively analyze the consistency of the abnormal equipment's operating status and the delay between generating the operation ticket to determine whether there is hysteresis information when generating the operation ticket; if there is no hysteresis information, the operation ticket is submitted to the operator for execution, and the corresponding operation instructions are issued.

Images