Method and system for processing monitoring data of box-type substation

Abstract

The invention discloses a box-type substation monitoring data processing method and system, and relates to the technical field of monitoring data processing, and the method comprises the steps: determining the type of monitoring data, constructing a monitoring data set and an abnormal fault set, and determining the correlation between the monitoring data set and the abnormal fault set; the method comprises the following steps: calculating a correlation index between monitoring data and an abnormal type, and a weight of each associated monitoring data in the abnormal type; a periodic monitoring strategy is adopted, data changes are captured in real time, abnormal values are screened out, and data fluctuation interference is eliminated through analysis; aiming at the quantity of initial monitoring data, adjusting and executing an anomaly detection strategy: comprehensively considering all anomaly types associated with the data when the data is single, and predicting a future anomaly risk by utilizing buffer time; when multiple data exist, completely matched anomaly judgment is preferentially carried out, and then whether anomaly judgment of single data needs to be carried out or not is judged; comprehensive and real-time monitoring and efficient abnormity early warning of the operation state of the box-type substation are realized, and the safe and stable operation capability of the substation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring data processing, and in particular to a method and system for processing monitoring data of a box-type substation. Background Art

[0002] Box-type substation (abbreviated as box-type substation) is a compact substation that integrates high-voltage switchgear, distribution transformers and low-voltage distribution equipment in a moisture-proof, rust-proof, dust-proof, rodent-proof, fire-proof, theft-proof, heat-insulated, fully enclosed, movable steel structure box; it has the characteristics of compact structure, easy installation, reliable performance and beautiful appearance, and is particularly suitable for urban network construction and transformation, as well as mines, factories, enterprises, oil and gas fields and wind power stations, etc., becoming a new type of complete set of power distribution equipment;

[0003] As an important part of the power system, the safe and stable operation of the box-type substation is crucial to ensuring the reliability of the power grid and the quality of electricity consumption for users. However, the box-type substation will be affected by a variety of internal and external factors during operation, such as fluctuations in electrical parameters, changes in ambient temperature and humidity, and equipment aging, which may cause failures or abnormal conditions in the substation. Therefore, real-time monitoring and data processing of the box-type substation to timely discover and warn of potential failures are of great significance for improving the operational reliability of the substation and reducing maintenance costs.

[0004] Traditional box-type substation monitoring data processing methods mostly rely on limited sensors and cannot fully capture various key data during the operation of the box-type substation, which may lead to an incomplete understanding of the overall operating status of the substation; in addition, traditional box-type substation monitoring data processing methods mostly do not make comprehensive judgments based on the weights of related monitoring data, but instead view each monitoring data in isolation, which may lead to misjudgment of abnormal situations because some anomalies may be caused by slight changes in multiple parameters; finally, traditional box-type substation monitoring data processing methods are often unable to predict the types of anomalies that may occur based on initial monitoring data, and can only be discovered when the anomaly actually occurs, which causes managers to be in a passive position when dealing with faults and unable to take measures to intervene in advance. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In response to the technical problems in the background technology, the present invention proposes a box-type substation monitoring data processing method and system, which selects multiple types of monitoring data, constructs a monitoring data set and an abnormal fault set, calculates the correlation index between each monitoring data and the corresponding abnormal type, and makes a comprehensive judgment based on the weight of the associated monitoring data; predicts the possible abnormal type based on the prediction and weight calculation of the associated monitoring data; and issues a warning signal in advance by calculating the buffer time, thereby solving the technical problems recorded in the background technology.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] A method for processing monitoring data of a box-type substation, comprising:

[0010] Determine the multiple types of data that need to be monitored during the operation of the box-type substation; construct monitoring data sets and abnormal fault sets, and establish the corresponding relationship between the monitoring data sets and the data in the abnormal fault sets;

[0011] Calculate the correlation index between each monitoring data and the corresponding abnormal type; calculate the weight of each associated monitoring data based on multiple associated monitoring data within each abnormal type;

[0012] Periodically monitoring the determined types of data, screening out all monitoring data whose monitoring values ​​exceed the corresponding first threshold at the end of each period, and determining whether the reason for exceeding the first threshold is data fluctuation, so as to screen out initial monitoring data;

[0013] Perform corresponding anomaly detection operations based on the number of initial monitoring data: When the number of initial monitoring data is single, filter out all the anomaly types corresponding to it, and based on the associated monitoring data of each anomaly type, predict in turn whether the corresponding anomaly will occur after the buffer time calculated by the initial monitoring data;

[0014] When there are multiple initial monitoring data, first consider the abnormal types that completely correspond to all or part of the initial monitoring data, and then perform abnormal type detection on the remaining single initial monitoring data in turn.

[0015] Specifically, the determined types of multiple monitoring data are put into the monitoring data set, and the monitoring data set is recorded as {A 1 ,A 2 ,…,A n}, where A i Represents the i-th data in the monitoring data set;

[0016] All abnormal types that occurred during the historical operation of the box-type substation are put into the abnormal fault set, and the abnormal fault set is recorded as {B 1 ,B 2 ,…,B m}, where B j Represents the jth data in the abnormal fault set.

[0017] Specifically, all monitoring data records when anomalies occur are obtained, and based on the set first threshold of each type of data, the correlation index between each monitoring data in the monitoring data set and the corresponding anomaly type is calculated. The expression is:

[0018] in, It represents the total number of times the jth type of abnormality in the abnormal fault set appears in the historical operation records of the box-type substation. It represents the total number of times that the i-th type of data in the monitoring data set exceeds the corresponding first threshold in all operation records of the j-th type of abnormality in the historical box-type substation abnormal fault set.

[0019] Furthermore, the monitoring data with a correlation index not equal to 0 with each type of anomaly are recorded as associated monitoring data of the corresponding anomaly type, and each associated monitoring data records these anomalies as their respective associated anomaly types;

[0020] Calculate the weight of each type of associated monitoring data based on the relevance index The expression is:

[0021] in, Represents the sum of the correlation indexes of all associated monitoring data of the jth type of anomaly in the abnormal fault set.

[0022] Specifically, at the end of each monitoring cycle, each type of recorded data value is compared with the corresponding first threshold value. When it is detected that the value of the monitoring data exceeds or is lower than the corresponding first threshold value, the monitoring values ​​of the monitoring data at the end of the previous several monitoring cycles are obtained, and based on the linear regression algorithm, it is determined whether a linear function of the monitoring data changing over time can be fitted; if a linear function can be fitted, the abnormality judgment strategy is executed; if a linear function cannot be fitted, it is determined whether the value monitored in the next monitoring cycle has returned to the normal value range. If it has returned to the normal value range, the monitoring data will not be recorded as the initial monitoring data.

[0023] Further, if the value detected in the next monitoring period has not returned to the normal value range, but the difference between the monitoring value and the first threshold is less than the difference between the monitoring value in the current monitoring period and the first threshold, then it is further determined whether data fluctuation occurs according to the monitoring value of the monitoring data in the next monitoring period;

[0024] If the value detected in the next monitoring cycle has not returned to the normal value range, and the difference between the monitoring value and the first threshold is not less than the difference between the monitoring value of the current monitoring cycle and the first threshold, the monitoring data is recorded as the initial monitoring data, and a linear function is fitted based on the linear regression algorithm according to the monitoring value of the current monitoring cycle and the monitoring values ​​of the next several monitoring cycles.

[0025] Specifically, at the end of a monitoring cycle, if there is initial monitoring data, the abnormality judgment strategy is executed. When only one initial monitoring data appears, all associated abnormality types of the initial monitoring data are sequentially taken out, and the remaining associated monitoring data corresponding to each abnormality type are sequentially taken out;

[0026] Obtaining a first monitoring value of each associated monitoring data when a corresponding abnormal type occurs, and using a maximum value or a minimum value among a plurality of first monitoring values ​​as initial monitoring data and a second threshold value of each associated monitoring data;

[0027] Obtain a second threshold of the initial monitoring data, and calculate the difference between the current monitoring value of the monitoring data and the second threshold; based on the fitted linear function, calculate the buffer time required for the value of the initial monitoring data to change to the second threshold.

[0028] Furthermore, a linear function is fitted based on the monitoring value of each associated monitoring data remaining at the end of the previous several monitoring cycles; based on the fitted linear function, the fitting value of each remaining associated monitoring data after the buffer time is calculated, and compared with the corresponding second threshold, the associated monitoring data exceeding the corresponding second threshold or lower than the corresponding second threshold is recorded, and the sum of the weights of these associated monitoring data is added to the weight of the initial monitoring data to obtain the total prediction weight of the corresponding abnormal type in the current monitoring cycle like This means that based on the data of the current monitoring period, it is predicted that the corresponding abnormal type will not appear after the buffer time;

[0029] like It means that according to the data of the current monitoring period, it is predicted that the corresponding anomaly may occur after the buffer time, and further judgment is required. Specifically, the current monitoring period is marked with the corresponding anomaly. If the total prediction weight of the anomaly type obtained by the next monitoring period analysis is This means that based on the data of the next monitoring cycle, it is predicted that the corresponding abnormal type will appear after the buffer time;

[0030] like This means that based on the data of the current monitoring period, it is predicted that the corresponding abnormal type will appear after the buffer time.

[0031] Specifically, when multiple initial monitoring data appear at the same time, the abnormal type that completely corresponds to all or part of the initial monitoring data is screened out; if all the initial monitoring data completely correspond to one abnormal type, then based on the fitting function of each initial monitoring data, the buffer time required for the value of each initial monitoring data to change to the corresponding second threshold is calculated respectively;

[0032] Calculate the difference t between the maximum and minimum values ​​of multiple buffer times. If t<t 0 , it is predicted that the corresponding abnormal type will appear after the maximum buffer time; where t 0 Indicates the buffer time difference threshold;

[0033] If t≥t 0 , then determine whether some of the initial monitoring data completely corresponds to an abnormal type. If so, multiple buffer times are also calculated to make abnormal judgments; if not, perform abnormal predictions under each initial monitoring data.

[0034] A box-type substation monitoring data processing system, comprising:

[0035] A monitoring data determination module, used to determine the multiple types of data that need to be monitored during the operation of the box-type substation;

[0036] The corresponding relationship establishment module is used to construct the monitoring data set and the abnormal fault set, establish the corresponding relationship between the monitoring data set and the data in the abnormal fault set; calculate the correlation index between each monitoring data and the corresponding abnormal type; based on multiple associated monitoring data in each abnormal type, calculate the weight of each associated monitoring data;

[0037] The abnormality analysis module includes an initial monitoring data screening unit and an associated monitoring data prediction unit, wherein the initial monitoring data screening unit is used to periodically monitor the determined types of data, screen out all monitoring data whose monitoring values ​​exceed the corresponding first threshold at the end of each period, and respectively determine whether the reason for exceeding the first threshold is data fluctuation, so as to screen out the initial monitoring data;

[0038] The associated monitoring data prediction unit performs corresponding anomaly detection operations based on the number of initial monitoring data. When the number of initial monitoring data is single, all the corresponding anomaly types are screened out, and based on the associated monitoring data of each anomaly type, it is predicted in turn whether the corresponding anomaly will appear after the buffer time calculated by the initial monitoring data; when the number of initial monitoring data is multiple, the anomaly types that completely correspond to all or part of the initial monitoring data are considered first, and then the anomaly type detection of the remaining single initial monitoring data is performed in turn.

[0039] (III) Beneficial effects

[0040] The present invention provides a box-type substation monitoring data processing method and system, which has the following beneficial effects:

[0041] 1. Through detailed planning and placement of various types of sensors, comprehensive collection of various key data during the operation of the box-type substation is ensured, which avoids the measurement error that may be caused by a single sensor, thereby improving the accuracy of overall monitoring and providing a comprehensive data basis for subsequent abnormal analysis of the box-type substation;

[0042] 2. By constructing monitoring data sets and abnormal fault sets and establishing the corresponding relationship between them, in-depth analysis and intelligent judgment of the operating status of box-type substations are achieved; by calculating the correlation index between monitoring data and corresponding abnormal types and making comprehensive judgments based on the weights of related monitoring data, the actual operating status of the substation can be more accurately reflected, reducing the probability of false alarms and missed alarms;

[0043] 3. By setting the monitoring cycle and systematically collecting, preprocessing and comparing and analyzing data, not only the accuracy and validity of the data are ensured, but also the linear regression algorithm is used to dynamically analyze the monitoring data, effectively distinguishing data fluctuations from real anomalies, thereby improving the accuracy and timeliness of anomaly detection; this can timely discover potential problems in substation operation, provide managers with a reliable basis for decision-making, and help ensure the safe and stable operation of box-type substations;

[0044] 4. Through refined abnormal judgment strategies, not only can single or multiple initial monitoring data be accurately predicted, but also the possibility and urgency of abnormality can be effectively evaluated by combining historical operation data and linear regression analysis; by calculating the buffer time and the total prediction weight, it provides managers with a scientific early warning basis, which helps to timely discover and deal with potential faults, thereby significantly improving the operating safety and stability of the box-type substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flow chart of the steps of a box-type substation monitoring data processing method provided by the present invention;

[0046] Figure 2 A structural schematic diagram of a box-type substation monitoring data processing system provided by the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] refer to Figure 1 The present invention provides a method for processing monitoring data of a box-type substation, comprising:

[0049] Step 1: Determine the multiple types of data that need to be monitored during the operation of the box-type substation; construct a monitoring data set and an abnormal fault set, and establish a corresponding relationship between the monitoring data set and each data in the abnormal fault set; calculate the correlation index between each monitoring data and the corresponding abnormal type; based on multiple associated monitoring data in each abnormal type, calculate the weight of each associated monitoring data;

[0050] The step one includes the following steps:

[0051] Step 101: placing multiple types of sensors in the box-type substation to obtain various data during the operation of the box-type substation;

[0052] The various data of the box-type substation during operation include electrical parameter data, internal and external environmental data, oil level and oil quality data, insulation performance data and other data, among which the electrical parameter data include high-voltage side voltage, current and power, low-voltage side voltage, current and power, bus voltage, phase voltage, line voltage, zero-sequence voltage and current, current harmonic content, etc.; internal and external environmental data include temperature and humidity inside the box-type substation, transformer winding temperature, oil temperature, wire contact point temperature, etc.; oil level and oil quality data include oil level in the transformer and gas content in the oil, etc.; insulation performance data include insulation resistance and breakdown voltage of transformer oil, insulation resistance and dielectric loss of each equipment in the box-type substation, etc.; other data include the number of discharges of the arrester and the speed of the internal fan, etc.; the equipment in the box-type substation includes transformers, mutual inductors, arresters, capacitors, etc.;

[0053] For the various data during the operation of the above-mentioned box-type substation, different types of sensors are used to monitor the corresponding data, and the sensors are placed at designated locations, specifically: the voltage, current and power on the high-voltage side and the voltage, current and power on the low-voltage side are respectively monitored in real time using Hall current sensors, electromagnetic voltage transformers and power factor meters; the sensors corresponding to the voltage, current and power on the high-voltage side are installed in the high-voltage switch cabinet and close to the high-voltage bus or cable connection; the sensors corresponding to the voltage, current and power on the low-voltage side are installed in the low-voltage switch cabinet and close to the low-voltage bus or cable connection;

[0054] The bus voltage, phase voltage and line voltage are monitored separately using voltage sensors in the bus voltage detection device, which is installed near the bus;

[0055] Zero-sequence voltage and current are monitored in real time using zero-sequence voltage sensors and zero-sequence current transformers, respectively, and are installed near the grounding system;

[0056] The amount of current harmonics is monitored in real time by harmonic current sensors, which are installed near all sensors used to detect current;

[0057] The temperature and humidity inside the box-type substation are monitored by temperature sensors and humidity sensors respectively, and one temperature sensor and one humidity sensor are installed on the inner wall of the high-voltage room, low-voltage room, transformer room and box-type substation box respectively;

[0058] The transformer winding temperature and oil temperature are monitored by fluorescent fiber optic temperature sensors, which are installed on the transformer winding wall and oil channel wall respectively; the wire contact point temperature is monitored by infrared temperature sensors, which are installed near the wire contact points where it is difficult to directly install sensors;

[0059] The transformer oil level is monitored by a magnetic flap oil level gauge installed on the transformer oil tank; the gas content in the oil is monitored by a gas online monitoring device installed near the transformer oil tank and connected to the oil tank through an oil pipe to detect the gas content in the oil in real time;

[0060] The insulation resistance and breakdown voltage of transformer oil are monitored by an insulating oil withstand voltage tester, which is placed near the selected transformer oil sampling point; the insulation resistance and dielectric loss of the equipment are monitored by a megohmmeter, which is placed near the equipment to be tested;

[0061] The number of discharges of the lightning rod is updated by monitoring the discharge situation in real time. The speed of the internal fan is monitored by the fan speed sensor.

[0062] Step 102: Put the various types of monitoring data obtained above into the monitoring data set. The temperature data at different locations are different types of data. The insulation resistance, dielectric loss and operation time data of different equipment are different types of data. Perform standard deviation calculation on various types of voltage data and current data, and record the results as the corresponding voltage and current fluctuation values. These data are also put into the monitoring data set. The monitoring data set is recorded as {A 1 ,A 2 ,…,A n}, where A i Represents the i-th data in the monitoring data set;

[0063] Step 103, establish an abnormal fault set, which stores all abnormal conditions that may occur in the box-type substation, including overheating of the box-type substation, failure of the box-type transformer on-load switch, tripping failure of the box-type transformer low-voltage switch, busbar failure, overheating of transformer windings, degradation of transformer oil insulation performance, poor ventilation and heat dissipation, abnormal high (low) voltage measurement data, etc.; the abnormal fault set is recorded as {B 1 ,B 2 ,…,Bm}, where B j Represents the jth data in the abnormal fault set;

[0064] Step 104: Establish a corresponding relationship between the monitoring data set and each data in the abnormal fault set, obtain all monitoring data records when abnormalities occur from the historical operation data of the box-type substation, and calculate the correlation index between each monitoring data in the monitoring data set and the corresponding abnormal type based on the set first threshold of each type of data. The expression is:

[0065] in, It represents the total number of times the jth type of abnormality in the abnormal fault set appears in the historical operation records of the box-type substation. Indicates the total number of times that the i-th type of data in the monitoring data set exceeds the corresponding first threshold in all operation records of the j-th type of abnormality in the abnormal fault set of the historical box-type substation; the first threshold of each type of data is set by the substation staff to determine whether further judgment of the abnormality is required;

[0066] Step 105: Record the monitoring data whose correlation index with each type of anomaly is not 0 as the associated monitoring data of the corresponding anomaly type. Similarly, these associated monitoring data will record these anomalies as their respective associated anomaly types. One type of anomaly can have multiple associated monitoring data at the same time, and one type of monitoring data can also have multiple associated anomaly types at the same time.

[0067] Calculate the weight of each type of associated monitoring data based on the relevance index The weight is used to make a comprehensive judgment on whether the corresponding abnormality occurs and the weight of the associated monitoring data. The expression is:

[0068] in, Represents the sum of the correlation indexes of all associated monitoring data of the jth type of anomaly in the abnormal fault set.

[0069] When using, combine the contents in step 101 to step 105:

[0070] Through detailed planning and placement of multiple types of sensors, comprehensive collection of various key data during the operation of the box-type substation is ensured, which avoids the measurement error that may be caused by a single sensor, thereby improving the accuracy of overall monitoring and providing a comprehensive data basis for subsequent abnormal analysis of the box-type substation;

[0071] By constructing monitoring data sets and abnormal fault sets and establishing the corresponding relationship between them, in-depth analysis and intelligent judgment of the operating status of the box-type substation are achieved; by calculating the correlation index between the monitoring data and the corresponding abnormal type, and making a comprehensive judgment based on the weight of the associated monitoring data, it can more accurately reflect the actual operating status of the substation and reduce the probability of false alarms and missed alarms.

[0072] Step 2: periodically monitor the determined data of various types, and at the end of each period, screen out all monitoring data whose monitoring values ​​exceed the corresponding first threshold value, and respectively determine whether the reason for exceeding the first threshold value is data fluctuation, so as to screen out the initial monitoring data; perform corresponding anomaly detection operations based on the number of initial monitoring data, and when the number of initial monitoring data is single, screen out all anomaly types corresponding thereto, and based on the associated monitoring data of each anomaly type, predict in turn whether the corresponding anomaly will appear after the buffer time calculated by the initial monitoring data; when the number of initial monitoring data is multiple, first consider the anomaly types that completely correspond to all initial monitoring data or part of the initial monitoring data, and then perform anomaly type detection on the remaining single initial monitoring data in turn;

[0073] The step 2 includes the following steps:

[0074] Step 201, set a monitoring cycle, monitor various types of data in step 101 at the end of each monitoring cycle and record specific values; for types of data that need to be calculated, such as voltage and current fluctuation values, perform corresponding calculations and record the calculation results;

[0075] Preprocess the collected raw data, including data cleaning (removing erroneous or invalid data), data calibration (making necessary corrections based on sensor characteristics), and data normalization (converting data of different dimensions to a unified standard) to ensure the accuracy and effectiveness of data analysis;

[0076] Step 202: At the end of each monitoring cycle, the recorded data values ​​of each type are compared with the corresponding first threshold value. When it is detected that the value of the monitoring data exceeds the corresponding first threshold value, it is determined whether the monitoring data exceeding the corresponding first threshold value is caused by fluctuations, specifically:

[0077] Obtain the monitoring values ​​of the monitoring data at the end of the previous several monitoring cycles, and based on the linear regression algorithm, fit a linear function of the monitoring data changing with time. If the linear function cannot be fitted, determine whether it is data fluctuation based on the monitoring value of the monitoring data in the next monitoring cycle. If the value detected in the next monitoring cycle has returned to the normal value range, it means that the monitoring data has experienced data fluctuation; the normal value range indicates a value range that does not exceed the corresponding first threshold, that is, the monitoring data value range when the corresponding device is operating normally;

[0078] If the value detected in the next monitoring period has not returned to the normal value range, but the difference between the monitoring value and the first threshold is less than the difference between the monitoring value in the current monitoring period and the first threshold, the same method is used to further determine whether data fluctuation occurs based on the monitoring value of the monitoring data in the next monitoring period;

[0079] If the value detected in the next monitoring cycle has not returned to the normal value range, and the difference between the monitoring value and the first threshold is not less than the difference between the monitoring value in the current monitoring cycle and the first threshold, it is determined that the box-type substation is abnormal, and the abnormality judgment strategy is executed;

[0080] After the abnormal judgment strategy is executed, a linear function is fitted based on the linear regression algorithm according to the monitoring values ​​of the current monitoring cycle and the monitoring values ​​of the next several monitoring cycles;

[0081] If a linear function can be fitted, it is judged that the box-type substation is abnormal and the abnormality judgment strategy is executed;

[0082] Step 203, execute the abnormality judgment strategy: record the monitoring data that exceeds the corresponding first threshold and is judged to have no data fluctuation as the initial monitoring data. If only one initial monitoring data appears at the end of a monitoring cycle, directly predict the remaining specified monitoring data, and take out each type of abnormality in the associated abnormality type in the order of the abnormal fault concentration, and take out the associated monitoring data corresponding to each type of abnormality in turn, and predict each associated monitoring data, specifically including:

[0083] Step 2031: For several associated monitoring data corresponding to the same type of abnormality, the initial monitoring data and the first monitoring value of each associated monitoring data when the corresponding abnormality type is determined to occur are obtained from the historical operation data of the box-type substation, that is, the first monitoring value, and the maximum value or the minimum value among the multiple first monitoring values ​​is used as the second threshold value of the initial monitoring data and each associated monitoring data; if the monitoring data is abnormal when it exceeds the first threshold value, the minimum value among the multiple first monitoring values ​​is used as the second threshold value of the corresponding monitoring data; if the monitoring data is abnormal when it is lower than the first threshold value, the maximum value among the multiple first monitoring values ​​is used as the second threshold value of the corresponding monitoring data;

[0084] Step 2032: Obtain a second threshold of the initial monitoring data, and calculate the difference between the current monitoring value of the monitoring data and the second threshold. Based on the linear function fitted in step 202, calculate the time required for the value of the initial monitoring data to change to the second threshold, that is, the buffer time;

[0085] Step 2033: similarly obtain the monitoring values ​​of each associated monitoring data at the end of the first several monitoring cycles, and perform linear function fitting respectively. It is necessary to ensure that the monitoring values ​​under the number of monitoring cycles obtained can be fitted to obtain a linear function. For example, for a certain associated monitoring data, a linear function cannot be obtained based on the monitoring values ​​under the first four monitoring cycles, but a linear function can be obtained based on the monitoring values ​​under the first three monitoring cycles, then a linear function is fitted based on the monitoring values ​​under the first three monitoring cycles;

[0086] Based on the buffer time calculated in step 2032, the fitting value of each associated monitoring data after the buffer time has passed is calculated, and compared with the corresponding second threshold, and the associated monitoring data exceeding the corresponding second threshold or lower than the corresponding second threshold is recorded, and the sum of the weights of these associated monitoring data is added to the weight of the initial monitoring data to obtain the total prediction weight of the corresponding abnormal type in the current monitoring period like This means that based on the data of the current monitoring period, it is predicted that the corresponding abnormal type will not appear after the buffer time;

[0087] like It means that according to the data of the current monitoring period, it is predicted that the corresponding anomaly may occur after the buffer time, and further judgment is required. Specifically, the current monitoring period is marked with the corresponding anomaly. If the total prediction weight of the anomaly type obtained by the next monitoring period analysis is This means that based on the data of the next monitoring cycle, it is predicted that the corresponding abnormal type will appear after the buffer time;

[0088] like This means that based on the data of the current monitoring period, it is predicted that the corresponding abnormal type will appear after the buffer time;

[0089] Step 2034, sequentially perform the operations from step 2031 to step 2033 for each type of abnormality in the associated abnormality type, so as to predict whether the corresponding abnormality type will occur in the box-type substation;

[0090] If multiple initial monitoring data appear at the same time at the end of a monitoring cycle, first screen the abnormal types corresponding to these initial monitoring data, and then determine whether it is necessary to predict other monitoring data values. The specific steps are:

[0091] Step 2131, filter out the abnormal types that completely correspond to all or part of the initial monitoring data, that is, the associated monitoring data corresponding to the filtered abnormal types are all initial monitoring data; if all the initial monitoring data completely correspond to one abnormal type, then based on the fitting function of each initial monitoring data, calculate the buffer time required for the value of each initial monitoring data to change to the corresponding second threshold value; if some of the initial monitoring data completely correspond to one abnormal type, then these initial monitoring data are taken out for analysis of the corresponding abnormal type, and similarly based on the fitting function of each initial monitoring data, calculate the buffer time required for the value of each initial monitoring data to change to the corresponding second threshold value, and the remaining initial monitoring data are respectively predicted according to steps 2031 to 2033 for abnormal prediction under each initial monitoring data; for example: if a certain At the end of a monitoring cycle, three initial monitoring data are identified. After further analysis, it is found that the three initial monitoring data completely correspond to the associated monitoring data of a certain abnormal type. Based on the fitting function of each initial monitoring data, the buffer time required for the value of each initial monitoring data to change to the corresponding second threshold is calculated respectively, and it is further determined whether the abnormal type has occurred; if it is found after further analysis that two of the three initial monitoring data completely correspond to the associated monitoring data of a certain abnormal type, then these two initial monitoring data are extracted, and based on the fitting function of the two initial monitoring data, the buffer time required for the value of each initial monitoring data to change to the corresponding second threshold is calculated respectively, and it is further determined whether the abnormal type has occurred. The remaining initial monitoring data is subjected to abnormal identification according to the operations in steps 2031 to 2033;

[0092] Step 2132: Calculate the difference t between the maximum and minimum values ​​of the buffering time. If t<t 0 , it means that the change trend of these initial monitoring data is the same as the change trend of the monitoring data under the corresponding abnormal type, and it is predicted that the corresponding abnormal type will appear after the maximum buffer time; where t 0 Indicates the buffer time difference threshold, which is set by the box-type substation manager;

[0093] If t≥t 0 , it means that the change trend of these initial monitoring data is different from the change trend of the monitoring data under the corresponding abnormal type, and it is necessary to separate these initial monitoring data for abnormal judgment, and judge whether there is part of the initial monitoring data that completely corresponds to an abnormal type. If so, perform abnormal judgment based on the operations of step 2131 to step 2132; if not, perform abnormal prediction under each initial monitoring data based on steps 2031 to step 2033;

[0094] Step 204: Based on the prediction results of each abnormal type, a warning of the corresponding abnormal type is sent.

[0095] When used, combine the contents in step 201 to step 204:

[0096] By setting the monitoring cycle and systematically collecting, preprocessing and comparing data, not only the accuracy and validity of the data are ensured, but also the linear regression algorithm is used to dynamically analyze the monitoring data, effectively distinguishing data fluctuations from real anomalies, thereby improving the accuracy and timeliness of anomaly detection; this can timely discover potential problems in substation operation, provide managers with a reliable basis for decision-making, and help ensure the safe and stable operation of box-type substations;

[0097] Through refined abnormal judgment strategies, not only can single or multiple initial monitoring data be accurately predicted, but also historical operation data and linear regression analysis can be combined to effectively evaluate the possibility and urgency of abnormal occurrence; by calculating the buffer time and the total prediction weight, it provides managers with a scientific early warning basis, which helps to timely discover and deal with potential faults, thereby significantly improving the operating safety and stability of box-type substations.

[0098] refer to Figure 2 The present invention also provides a box-type substation monitoring data processing system, comprising:

[0099] A monitoring data determination module, used to determine the multiple types of data that need to be monitored during the operation of the box-type substation;

[0100] The corresponding relationship establishment module is used to construct the monitoring data set and the abnormal fault set, establish the corresponding relationship between the monitoring data set and the data in the abnormal fault set; calculate the correlation index between each monitoring data and the corresponding abnormal type; based on multiple associated monitoring data in each abnormal type, calculate the weight of each associated monitoring data;

[0101] The abnormality analysis module includes an initial monitoring data screening unit and an associated monitoring data prediction unit, wherein the initial monitoring data screening unit is used to periodically monitor the determined types of data, screen out all monitoring data whose monitoring values ​​exceed the corresponding first threshold at the end of each period, and respectively determine whether the reason for exceeding the first threshold is data fluctuation, so as to screen out the initial monitoring data;

[0102] The associated monitoring data prediction unit performs corresponding anomaly detection operations based on the number of initial monitoring data. When the number of initial monitoring data is single, all the corresponding anomaly types are screened out, and based on the associated monitoring data of each anomaly type, it is predicted in turn whether the corresponding anomaly will appear after the buffer time calculated by the initial monitoring data; when the number of initial monitoring data is multiple, the anomaly types that completely correspond to all or part of the initial monitoring data are considered first, and then the anomaly type detection of the remaining single initial monitoring data is performed in turn.

[0103] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer storage medium or transmitted via a computer storage medium.

[0104] Computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. Computer storage media can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid state drives (SSDs)).

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for processing monitoring data of a box-type substation, characterized in that: include: Determine the multiple types of data that need to be monitored during the operation of the box-type substation; Construct monitoring data sets and abnormal fault sets, and establish the corresponding relationship between the monitoring data sets and the data in the abnormal fault sets; Calculate the correlation index between each monitoring data and the corresponding abnormal type; Based on multiple associated monitoring data within each abnormal type, calculate the weight of each associated monitoring data; Periodically monitoring the determined types of data, screening out all monitoring data whose monitoring values ​​exceed the corresponding first threshold at the end of each period, and determining whether the reason for exceeding the first threshold is data fluctuation, so as to screen out initial monitoring data; Perform corresponding anomaly detection operations based on the number of initial monitoring data: When the number of initial monitoring data is single, filter out all the anomaly types corresponding to it, and based on the associated monitoring data of each anomaly type, predict in turn whether the corresponding anomaly will occur after the buffer time calculated by the initial monitoring data; When there are multiple initial monitoring data, first consider the abnormal types that completely correspond to all or part of the initial monitoring data, and then perform abnormal type detection on the remaining single initial monitoring data in turn.

2. A method for processing monitoring data of a box-type substation according to claim 1, characterized in that: The determined types of multiple monitoring data are put into the monitoring data set, and the monitoring data set is recorded as {A1, A2, …, A n }, where A i Represents the i-th data in the monitoring data set; All abnormal types that occurred during the historical operation of the box-type substation are put into the abnormal fault set, and the abnormal fault set is recorded as {B1, B2,…, B m }, where B j Represents the jth data in the abnormal fault set.

3. A method for processing monitoring data of a box-type substation according to claim 2, characterized in that: Obtain all monitoring data records when anomalies occur, and calculate the correlation index between each monitoring data in the monitoring data set and the corresponding anomaly type based on the set first threshold of each type of data The expression is: in, It represents the total number of times the jth type of abnormality in the abnormal fault set appears in the historical operation records of the box-type substation. It represents the total number of times that the i-th type of data in the monitoring data set exceeds the corresponding first threshold in all operation records of the j-th type of abnormality in the historical box-type substation abnormal fault set.

4. A method for processing monitoring data of a box-type substation according to claim 3, characterized in that: The monitoring data with a correlation index not equal to 0 for each type of anomaly are recorded as the associated monitoring data of the corresponding anomaly type, and each associated monitoring data records these anomalies as their respective associated anomaly types; Calculate the weight of each type of associated monitoring data based on the relevance index The expression is: in, Represents the sum of the correlation indexes of all associated monitoring data of the jth type of anomaly in the abnormal fault set.

5. A method for processing monitoring data of a box-type substation according to claim 4, characterized in that: At the end of each monitoring cycle, the recorded data values ​​of each type are compared with the corresponding first threshold value. When it is detected that the value of the monitoring data exceeds or is lower than the corresponding first threshold value, the monitoring values ​​of the monitoring data at the end of the previous monitoring cycles are obtained, and based on the linear regression algorithm, it is determined whether a linear function of the monitoring data changing over time can be fitted; if a linear function can be fitted, the abnormality judgment strategy is executed; If a linear function cannot be fitted, it is determined whether the value monitored in the next monitoring period has returned to the normal value range. If it has returned to the normal value range, the monitoring data will not be recorded as the initial monitoring data.

6. A method for processing monitoring data of a box-type substation according to claim 5, characterized in that: If the value detected in the next monitoring period has not returned to the normal value range, but the difference between the monitoring value and the first threshold is less than the difference between the monitoring value in the current monitoring period and the first threshold, then further determine whether data fluctuation occurs based on the monitoring value of the monitoring data in the next monitoring period; If the value detected in the next monitoring cycle has not returned to the normal value range, and the difference between the monitoring value and the first threshold is not less than the difference between the monitoring value of the current monitoring cycle and the first threshold, the monitoring data is recorded as the initial monitoring data, and a linear function is fitted based on the linear regression algorithm according to the monitoring value of the current monitoring cycle and the monitoring values ​​of the next several monitoring cycles.

7. A method for processing monitoring data of a box-type substation according to claim 6, characterized in that: At the end of a monitoring cycle, if there is initial monitoring data, the abnormality judgment strategy is executed. When only one initial monitoring data appears, all associated abnormal types of the initial monitoring data are taken out in sequence, and the remaining associated monitoring data corresponding to each abnormal type are taken out in sequence; Obtaining a first monitoring value of each associated monitoring data when a corresponding abnormal type occurs, and using a maximum value or a minimum value among a plurality of first monitoring values ​​as initial monitoring data and a second threshold value of each associated monitoring data; Obtaining a second threshold value of the initial monitoring data, and calculating a difference between a current monitoring value of the monitoring data and the second threshold value; Based on the fitted linear function, the buffer time required for the value of the initial monitoring data to change to the second threshold is calculated.

8. A method for processing monitoring data of a box-type substation according to claim 7, characterized in that: Fitting a linear function based on the monitoring value of each associated monitoring data remaining at the end of the previous monitoring cycles; calculating the fitting value of each remaining associated monitoring data after the buffer time based on the fitted linear function, and comparing it with the corresponding second threshold, recording the associated monitoring data that exceeds the corresponding second threshold, or is lower than the corresponding second threshold, adding the sum of the weights of these associated monitoring data to the weight of the initial monitoring data, and obtaining the total prediction weight of the corresponding abnormal type in the current monitoring cycle like This means that based on the data of the current monitoring period, it is predicted that the corresponding abnormal type will not appear after the buffer time; like It means that according to the data of the current monitoring period, it is predicted that the corresponding anomaly may occur after the buffer time, and further judgment is required. Specifically, the current monitoring period is marked with the corresponding anomaly. If the total prediction weight of the anomaly type obtained by the next monitoring period analysis is This means that based on the data of the next monitoring cycle, it is predicted that the corresponding abnormal type will appear after the buffer time; like This means that based on the data of the current monitoring period, it is predicted that the corresponding abnormal type will appear after the buffer time.

9. A method for processing monitoring data of a box-type substation according to claim 7, characterized in that: When multiple initial monitoring data appear at the same time, the abnormal type that completely corresponds to all or part of the initial monitoring data is screened out; if all the initial monitoring data completely correspond to one abnormal type, then based on the fitting function of each initial monitoring data, the buffer time required for the value of each initial monitoring data to change to the corresponding second threshold is calculated respectively; Calculate the difference t between the maximum and minimum values ​​of multiple buffer times. If t<t0, it is predicted that the corresponding abnormal type will appear after the maximum buffer time; where t0 represents the buffer time difference threshold; If t≥t0, determine whether some of the initial monitoring data completely corresponds to an abnormal type. If so, calculate multiple buffer times to make an abnormal judgment. If not, perform an abnormal prediction under each initial monitoring data.

10. A box-type substation monitoring data processing system, characterized in that: include: A monitoring data determination module, used to determine the multiple types of data that need to be monitored during the operation of the box-type substation; A corresponding relationship establishment module is used to construct a monitoring data set and an abnormal fault set, and establish a corresponding relationship between each data in the monitoring data set and the abnormal fault set; Calculate the correlation index between each monitoring data and the corresponding abnormal type; Based on multiple associated monitoring data within each abnormal type, calculate the weight of each associated monitoring data; An abnormal analysis module, including an initial monitoring data screening unit and a related monitoring data prediction unit; The initial monitoring data screening unit is used to periodically monitor the determined types of data, screen out all monitoring data whose monitoring values ​​exceed the corresponding first threshold at the end of each period, and determine whether the reason for exceeding the first threshold is data fluctuation, so as to screen out the initial monitoring data; The associated monitoring data prediction unit performs corresponding anomaly detection operations based on the number of initial monitoring data. When the number of initial monitoring data is single, all the corresponding anomaly types are screened out, and based on the associated monitoring data of each anomaly type, it is predicted in turn whether the corresponding anomaly will appear after the buffer time calculated from the initial monitoring data; when the number of initial monitoring data is multiple, the anomaly types that completely correspond to all or part of the initial monitoring data are considered first, and then the anomaly type detection of the remaining single initial monitoring data is performed in turn.

Images