Hierarchical comprehensive evaluation-based power distribution network automation switch health state evaluation method and system

Abstract

The invention discloses a power distribution network automation switch health state evaluation method and system based on hierarchical comprehensive evaluation. The method comprises the steps of obtaining ledger and measurement data of a line, a switch and a distribution transformer, uploading signal data of the automation switch, line fault power failure, transfer and operation ticket records; extracting health state features from the acquired data and labeling feature tags; according to the extracted switch health state features, using an analytic hierarchy process to solve the weight of each feature tag item, and establishing a comprehensive evaluation model; and performing batch evaluation on the health state of each automatic switch by using the comprehensive evaluation model. Based on related data of the automatic switch, the health state of the automatic switch is reasonably evaluated through the comprehensive evaluation model, and available, usable and easy-to-use data are provided for companies.

Description

Technical Field

[0001] The present invention belongs to the field of medium-voltage distribution network switch-level data quality analysis, and specifically relates to a distribution network automation switch health status assessment method and system based on hierarchical comprehensive evaluation. Background Art

[0002] The distribution network directly faces the end customers and is a key link that affects the level of power supply services. When a distribution line fails, if the fault point is not identified and isolated in time, the scope of the power outage will expand and the customer's electricity quality will also decrease.

[0003] The existing technology does not mark and evaluate the availability of automation switch data and the rationality of point distribution, which leads to errors in judgment caused by interference factors when users use or refer to automation switch ledgers, measurements, signals, and point distribution related data. For example, it will cause misjudgment of the scope of power outages, making it impossible to determine solutions in time, differences in data format and accuracy between automation switch equipment from different manufacturers will lead to misleading data integration analysis, and unreasonable point distribution will lead to an expansion of the scope of faults. In order to further improve the data collection and availability of automation switches and assist in decision-making on the reliable operation of distribution networks, the data quality evaluation of automation switches is crucial and needs to be solved urgently. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide a method and system for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation, which can solve the problem that the prior art cannot accurately evaluate the rationality of the data sent by the automation switches and the layout of the points.

[0005] Technical solution: A method for evaluating the health status of a distribution network automation switch based on hierarchical comprehensive evaluation of the present invention comprises:

[0006] Data acquisition: obtain the ledger and measurement data of lines, switches, distribution transformers, signal data sent by automatic switches, and records of line failure power outages, power transfers, and operation tickets;

[0007] Extraction of health status by item: Extract health status features from the acquired data and add feature labels, where health status features include switch voltage measurement status, current measurement status, power measurement status, switch protection and opening and closing transmission status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, switch FA positioning fault interval accuracy status;

[0008] Model establishment: Based on the extracted health status characteristics of each switch, the weight of each feature label item is calculated using the hierarchical analysis method, and a comprehensive evaluation model is established;

[0009] Health status assessment: Use a comprehensive evaluation model to conduct batch assessment of the health status of each automation switch.

[0010] Furthermore, the records and measurement data of the lines, switches, and distribution transformers include basic information maintained by the lines, switches, and distribution transformers in the PMS system, marketing system, and distribution automation system, power measurement, power factor value, voltage measurement, and current measurement data of switches and distribution transformers, and topological connection relationship data of lines, switches, and distribution transformers;

[0011] The signal data sent by the automatic switch includes protection signals, opening and closing signals, FA fault areas, FA tests and switch listing information sent by all automatic switches in the distribution network of the distribution automation system;

[0012] The line fault power outage, transfer, and operation ticket records include line fault information, line power outage related information in the power outage reliability system, packaged data information applied by the city and prefecture of the line loss system, and operation ticket records filled in by the city and prefecture.

[0013] Furthermore, health status features are extracted from the acquired data and labeled with features, including:

[0014] By checking the missing and abnormal conditions of the automatic switch voltage measurement, the switch voltage measurement status characteristic label is established;

[0015] By checking the missing and abnormal conditions of the automatic switch current measurement, the switch current measurement status characteristic label is established;

[0016] By checking the missing and abnormal conditions of the automatic switch power measurement, the switch power measurement status characteristic label is established;

[0017] By checking the automatic switch action signal sent by the distribution automation system, the quality status characteristic label of the switch opening and closing signal is established;

[0018] The automation switch type label status is established by verifying the consistency of the switch type maintained by the automation switch in the PMS system and the distribution automation system.

[0019] Furthermore, health status features are extracted from the acquired data and labeled with features, including:

[0020] Combine the switch signal and measurement data to check the switch operation status, and establish two status characteristics: switch operation label status and switch point table status;

[0021] By counting the number of downstream distribution variables of the automated switch, a rationality status label for the switch hierarchical protection layout is established.

[0022] Furthermore, health status features are extracted from the acquired data and labeled with features, including:

[0023] By finding out whether there is a hierarchical protection switch in the topological upstream of the fault area identified by FA, ​​a status label of the rationality of the coordination between the hierarchical protection of the switch and FA is established;

[0024] By finding out whether there is a first switch in the fault area located by FA in the topology upstream of the first switch in the fault area formed by the most downstream protection alarm switch, a switch FA location fault interval accuracy label is established.

[0025] Furthermore, the weight of each feature label item is obtained by using the hierarchical analysis method according to the extracted health status characteristics of each switch, and a comprehensive evaluation model is established, including:

[0026] The feature label data of the automation switch is integrated and extracted to form an evaluation sample set for the health status of the automation switch. The weight of each feature label item is obtained according to the hierarchical analysis method, and a comprehensive evaluation model is established.

[0027] Furthermore, a comprehensive evaluation model is used to batch evaluate the health status of each automation switch, including:

[0028] Based on the obtained weights of each feature label item, batches of label item feature data are generated for each automation switch and the required feature value evaluation weights are calculated. The data are sent to the comprehensive evaluation model for calculation, and finally the data health status assessment results corresponding to each automation switch are output.

[0029] Based on the same inventive concept, a distribution network automation switch health status assessment system based on hierarchical comprehensive evaluation of the present invention comprises:

[0030] Data acquisition module, used to obtain the ledger and measurement data of lines, switches, distribution transformers, signal data sent by automatic switches, and records of line fault power outages, power transfers, and operation tickets;

[0031] The health status sub-item extraction module is used to extract health status features from the acquired data and label them with features, where the health status features include switch voltage measurement status, current measurement status, power measurement status, switch protection and opening and closing transmission status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, and switch FA positioning fault interval accuracy status;

[0032] The model building module is used to obtain the weight of each feature label item based on the extracted health status characteristics of each switch using the hierarchical analysis method and establish a comprehensive evaluation model;

[0033] The health status assessment module is used to batch assess the health status of each automation switch using a comprehensive evaluation model.

[0034] Based on the same inventive concept, the present invention provides a distribution network automation switch health status assessment device based on hierarchical comprehensive evaluation, including a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the distribution network automation switch health status assessment method based on hierarchical comprehensive evaluation as described above.

[0035] Based on the same inventive concept, a computer-readable storage medium of the present invention stores a computer program thereon, and when the program is executed by a processor, the steps of the above-mentioned method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation are implemented.

[0036] Beneficial effects: Compared with the prior art, the significant technical effects of the present invention are:

[0037] The present invention learns the changing characteristics of massive historical data in a data-driven manner, combines multi-source data such as line operation or fault records, switch and distribution variable measurement data, multi-system ledger data, switch signal transmission records, etc., and extracts a total of 11 relevant feature labels related to the health status of the switch. The comprehensive evaluation model is used to reasonably evaluate the quality of the actual switch data, thus avoiding the problem of a large amount of dirty, messy and poor data when using switch data to a certain extent.

[0038] The present invention comprehensively considers the data quality of various aspects of the switch, switch measurement, signal upload events, basic equipment information, equipment layout linkage and other data characteristics, and comprehensively evaluates the health status information of each switch with high credibility.

[0039] The present invention can be used to mark the data health status of all automated switches. The calculation is simple and the principle is clear. It can help distribution network operators to timely discover the equipment operation status and data transmission status, and can provide effective data for distribution network operators and data-related users to assist in scientific decision-making. It can effectively help improve the quality of basic data of distribution networks, support the construction of smart distribution networks, and has good application prospects.

[0040] Build a comprehensive evaluation model to achieve the labeling of the health status of power grid switch-level data, help provide the company with available, usable and easy-to-use data, assist decision-making in accurately and quickly locating fault areas, reduce on-site inspections and other operations to improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic flow chart of a method for evaluating the health status of a distribution network automation switch based on hierarchical comprehensive evaluation disclosed in an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of the structure of a distribution network automation switch health status assessment system based on hierarchical comprehensive evaluation disclosed in an embodiment of the present invention;

[0043] Figure 3 The present invention discloses a structural diagram of a device for evaluating the health status of a distribution network automation switch based on hierarchical comprehensive evaluation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The technical solution of the present invention is described in detail below in conjunction with specific implementation methods and the accompanying drawings.

[0045] See also Figure 1 , Figure 1 The present invention discloses a flow chart of a method for evaluating the health status of a distribution network automation switch based on hierarchical comprehensive evaluation. Figure 1 The described method for evaluating the health status of a distribution network automation switch is applied to a power system, such as evaluating the health status of a distribution network automation switch with multi-source data, etc., which is not limited in the embodiments of the present invention. Figure 1 As shown, the distribution network automation switch health status assessment method based on hierarchical comprehensive evaluation may include the following operations:

[0046] S1. Data acquisition: obtain the records and measurement data of lines, switches, and distribution transformers, the signal data sent by automatic switches, and the records of line fault power outages, power transfers, and operation tickets.

[0047] Among them, the records and measurement data of lines, switches, and distribution transformers include the basic information of lines, switches, and distribution transformers maintained in the power information collection system (pms), marketing system, and distribution automation system, power measurement, power factor value, voltage measurement, and current measurement data of switches and distribution transformers, and topological connection relationship data of lines, switches, and distribution transformers. In this embodiment, the distribution automation system is specifically the D5200 system.

[0048] In this embodiment, the ledger data of lines, switches, and distribution transformers: the distribution transformer and line topology association, equipment commissioning information, point meter status, installation status of various terminals, and other ledger data are exported in the marketing system, D5200, and power consumption information collection system;

[0049] Switch measurement data: The D5200 system exports the switch active power, current, and voltage measurement data sampled every 15 minutes;

[0050] Line measurement data: The active power measurement data of the line sampled every 15 minutes is exported in the D5000 system. The sampling frequency of sampling every 15 minutes can be modified according to the actual situation.

[0051] Measurement data of distribution transformer: the distribution transformer ledger data is exported in the power consumption information collection system; the active power measurement data of the distribution transformer is sampled every 15 minutes. The aforementioned sampling frequency of sampling every 15 minutes can be modified according to actual conditions.

[0052] The signal data sent by the automatic switch includes the protection signal, opening and closing signal, FA (feeder automation) fault area, FA test and switch listing information sent by all the automatic switches in the D5200 system distribution network.

[0053] Line fault power outage, supply transfer, and operation ticket records include fault information of lines related to the customer service power outage information release, line power outage related information within the power outage reliability system, packaged data information applied by cities and prefectures for the line loss system, and operation ticket records filled out by cities and prefectures.

[0054] In this embodiment, customer service-related fault event records and operation ticket records are obtained in the provincial communication system; the city package transfer records within the system during the same period are obtained; the distribution transformer and line-level power outage event records within the power outage reliability system are obtained; the above-mentioned systems are systems existing in the prior art.

[0055] S2. Extraction of health status sub-items: Extract health status features from the acquired data and add feature labels, where the health status features include switch voltage measurement status, current measurement status, power measurement status, switch protection and opening and closing transmission status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, and switch FA fault interval positioning accuracy status.

[0056] In this embodiment, 11 feature labels are extracted, including switch voltage measurement status, current measurement status, power measurement status, switch protection and switching uploading status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, and switch FA positioning fault interval accuracy status, including the following sub-steps:

[0057] S2.1. Establish switch voltage measurement status characteristics: Establish switch voltage measurement status characteristic labels by checking the missing and abnormal conditions of automatic switch voltage measurement; the details are as follows:

[0058] Switch SW k The voltage measurement data is U k =[u k,1 ,u k,2 ,…,u k,i ,…,u k,m ], m represents the number of sampling points of switch voltage measurement data;

[0059] For switch SW k Time collection k,j Check the voltage data to see if there are any abnormalities below. If so, record it as the abnormal time point:

[0060] Abnormal situation 1: No data was collected;

[0061] Abnormal situation 2: The voltage value is zero, the same as the value at other time points on the day;

[0062] Abnormal situation 3: The voltage value is negative;

[0063] Abnormal situation 4: The voltage value is the same as the data of the previous 10 sampling points and the value is greater than zero;

[0064] Abnormal situation 5: The difference between the voltage value and the value measured at the same time in the three-zone historical database is more than 20%;

[0065] Abnormal situation 6: The voltage value is zero or empty for 5 or more days among the sampling points at the same time in the previous 7 days;

[0066] Abnormal situation 7: The voltage value drops to zero or is empty for 5 or more times during the day;

[0067] Abnormal situation 8: The voltage value of the sectionalizer is zero or empty, but there is no power outage in the downstream distribution transformer and there is no tie switch. The definition of no power outage in the distribution transformer is: the distribution transformer simultaneously meets the conditions of no power outage event for users and users, no power outage event for the fusion terminal, no power outage in the power outage reliability system, and no planned or fault power outage record for the line to which it belongs;

[0068] Abnormal situation 9: The voltage value of the tie switch is non-zero and non-empty, but there is no tie switch change signal or transfer record;

[0069] Traversal switch SW k The voltage data of each sampling point is used to calculate the switch SW k The number of sampling abnormal time points;

[0070] Traverse all switches and find the number of abnormal time points of the sampling points of each switch;

[0071] According to the abnormal time points of each switch voltage measurement collection, the quartile method is used to divide it into four labels: extremely low health, low health, medium health, and high health;

[0072] Finally, all switches are labeled with switch voltage measurement health status, and the characteristic labels are divided into four types: extremely low health, low health, medium health, and high health.

[0073] S2.2. Establish switch current measurement status characteristics: Establish switch current measurement status characteristic labels by checking the missing and abnormal conditions of automatic switch current measurement; the details are as follows:

[0074] Switch SW k The current measurement data is I k =[i k,1 ,i k,2 ,…,i k,i ,…,i k,m ], m represents the number of sampling points of switch current measurement data;

[0075] For switch SW k Time Collection k,j Check the current data to see if there are any abnormal conditions below. If so, record it as the abnormal time point:

[0076] Abnormal situation 1: No data was collected;

[0077] Abnormal situation 2: The current value is the same as the data of the previous 10 sampling points and the value is neither zero nor empty;

[0078] Abnormal situation 3: The difference between the current value converted into success rate and the power value collected at the same time is more than 2 times;

[0079] Abnormal situation 4: The difference between the current value and the value of the downstream distribution transformer at the same time is more than 2 times;

[0080] Abnormal situation 5: The difference between the current value and the value measured at the same time in the three-zone historical database is more than 20%;

[0081] Abnormal situation 6: The current value is empty or has the same value for 5 or more days among the sampling points at the same time in the previous 7 days;

[0082] Abnormal situation 7: The current value is empty for 5 or more times in the same day;

[0083] Abnormal situation 8: The current value of the sectionalizer is zero or empty, but there is no power outage in the downstream distribution transformer and there is no tie switch. The definition of no power outage in the distribution transformer is: the distribution transformer simultaneously meets the conditions of no power outage event for users and users, no power outage event for the fusion terminal, no power outage in the power outage reliability system, and no planned or fault power outage record for the line to which it belongs;

[0084] Abnormal situation 9: The current value of the tie switch is non-zero and non-empty, but there is no tie switch position change signal or transfer record;

[0085] Traversal switch SW k The current data of each sampling point is used to calculate the switch SW k The number of sampling abnormal time points;

[0086] Traverse all switches and find the number of abnormal time points of the sampling points of each switch;

[0087] According to the abnormal time points of each switch current measurement collection, the quartile method is used to divide it into four labels: extremely low health, low health, medium health, and high health;

[0088] Finally, all switches are labeled with switch current health status characteristic labels, which are divided into four types: extremely low health, low health, medium health, and high health.

[0089] S2.3. Establish switch active power measurement status characteristics: Establish switch power measurement status characteristic labels by checking the missing and abnormal conditions of automatic switch power measurement; the details are as follows:

[0090] Switch SW k The active power measurement data is P k =[p k,1 ,p k,2 ,…,p k,i ,…,p k,m ], m represents the number of sampling points of the switch active power measurement data. Note that the active power measurement here is the actual power consumption after multiplying the power factor value;

[0091] For switch SW k Time collection k,j Check the active power data to see if there is any abnormality. If so, record it as the abnormal time point. The abnormality here is the same as the 9 abnormalities diagnosed in the current value in step 2.

[0092] Traversal switch SW k Active power data of each sampling point, calculate switch SW k The number of sampling abnormal time points;

[0093] Traverse all switches and find the number of abnormal time points of the sampling points of each switch;

[0094] According to the abnormal time points of active power measurement collection of each switch, the quartile method is used to divide it into four labels: extremely low health, low health, medium health, and high health;

[0095] Finally, all switches are labeled with the switch active power measurement health status, and the characteristic labels are divided into four types: extremely low health, low health, medium health, and high health.

[0096] S2.4. Establish the status characteristics of the switch hierarchical protection event upload, as follows:

[0097] Switch SW k The hierarchical protection event data sent is F k =[ek,1 ,e k,2 ,…,i k,i ,…,i k,m ], m represents the number of hierarchical protection events sent by the switch. Note that events during FA testing and switch hanging period must be excluded;

[0098] For switch SW k Check whether the following abnormal conditions exist in the sent hierarchical protection events. If so, record them as abnormally sent hierarchical protection events:

[0099] Abnormal situation 1: The switch sends 4 or more graded protection events within 15 seconds;

[0100] Abnormal situation 2: The switch sends more than 100 graded protection events on the same day;

[0101] Abnormal situation 3: The same terminal sends 2 or more classified protection events within 10 seconds;

[0102] Abnormal situation 4: The same type of graded protection events of the switch are reported at the same time in 3 or more days in the previous 7 days;

[0103] Abnormal situation 5: The switch has the function of sending opening and closing signals, and has the function of sending graded protection signals, but does not send any protection events;

[0104] Traversal switch SW k All the hierarchical protection events sent up, ask for switch SW k The number of abnormal events sent to the hierarchical protection department;

[0105] Traverse all switches to obtain the number of uploading hierarchical protection events and the ratio of the number of uploading abnormal hierarchical protection events to the total number of uploading hierarchical protection events for each switch;

[0106] According to the proportion of abnormal protection events sent to each switch, the quartile method is used to divide the switches into four labels: extremely low health, low health, medium health, and high health.

[0107] Finally, all switches are labeled with graded protection events and sent to health status tags. The characteristic tags are divided into four types: extremely low health, low health, medium health, and high health.

[0108] S2.5. Establish the status characteristics of the switch opening and closing events: by verifying the automatic switch action signal sent by the D5200 system, establish the quality status characteristic label of the switch opening and closing signal; the details are as follows:

[0109] Switch SW k The data of the opening and closing events sent up is E k =[e k,1,s ,e k,1,e ,ek,2,s ,e k,2,e ,…,i k,i,s ,i k,i,e ,…,i k,m,s ,i k,m,e ], m represents the number of opening and closing events sent by the switch, s represents the opening event of the switch, and e represents the closing event of the switch. Note that events during the FA test and switch listing period must be excluded;

[0110] For switch SW k For the sent opening and closing events, check whether there are any of the following abnormal conditions. If so, record it as an abnormal sent power outage event:

[0111] Abnormal situation 1: only the upper-send opening event or only the upper-send closing event;

[0112] Abnormal situation 2: The opening and closing time of the opening and closing event differ by more than 15 minutes, but the voltage value of the automatic switch at the corresponding time is not zero or empty, there is no tie switch downstream, and there is no related fault, transfer and power outage record in the distribution transformer and line-level power outage events;

[0113] Abnormal situation 3: The switch is opened or closed 4 times or more within 15 seconds;

[0114] Abnormal situation 4: The switch is opened or closed more than 100 times on the same day;

[0115] Abnormal situation 5: There are two or more position changes within 10 seconds on the same terminal;

[0116] Abnormal situation 6: The opening and closing events sent by the switch are sent at the same time for 3 or more days in the previous 7 days;

[0117] Abnormal situation 7: The switch sends and opens the switch, but there is no fault on the line. The line fault is defined as: there is a power outage event record of the distribution transformer downstream of the switch in the power outage reliability system, or there is a line power outage event, or there is a line fault record, or there is a line transfer record, or there is an operation ticket record;

[0118] Abnormal situation 8: The switch has a classified protection event, but no opening and closing signal is sent;

[0119] Abnormal situation 9: The switch is continuously opened or closed;

[0120] Abnormal situation 10: There are opening and closing events between 23:00 at night and 7:00 in the morning, but there is no record of the same time in the corresponding fault, plan, or power outage events;

[0121] Abnormal situation 11: In the fault and power outage event records in the power supply reliability system, transfer system, and operation ticket system, the period of plus or minus thirty minutes from the start time of the fault / power outage is used as the standard. If there is an automatic switch in the fault / power outage section, but there is no automatic switch up-but-close event, it is an abnormality;

[0122] Traversal switch SW k All the opening and closing data sent up, find the switch SW k The number of abnormal opening and closing events sent upward;

[0123] Traverse all switches to obtain the number of abnormal up-sending opening and closing events of each switch and the ratio of the number of abnormal up-sending opening and closing events to the total number of up-sending opening and closing events;

[0124] According to the proportion of abnormal number of opening and closing events of each switch, the quartile method is used to divide it into four labels: extremely low health, low health, medium health, and high health;

[0125] Finally, all switches are labeled with status feature labels of switch opening and closing events. The feature labels are divided into four types: extremely low health, low health, medium health, and high health.

[0126] S2.6. Establish switch type status feature label: Establish the switch type label status label of the automation switch by verifying the consistency of the switch type maintained in the PMS system and the D5200 system; the details are as follows:

[0127] Obtain the records of all switches in the D5200 system and the PMS system, and check the switch categories and models of the switch automation types maintained in the two systems. If they are inconsistent, the switch type quality status is poor, otherwise the switch type quality status is good;

[0128] Finally, the type status quality labels of all switches are obtained, which are divided into two types: better and worse.

[0129] S2.7. Establish switch operation status characteristic label: Combine switch signals, measurements and other data to verify the switch operation status and establish switch operation label status characteristics; the details are as follows:

[0130] Based on the switch operation status data obtained in the PMS system and D5200 system, as well as the switch measurement data, check whether the following abnormal conditions exist. If so, record it as an abnormal switch operation status:

[0131] Abnormal situation 1: Get the voltage measurement value of the switch in the past day. If there is a measurement data record for the switch, but the switch is not in operation in the system, it is considered that the switch is abnormal in operation, otherwise it is normal;

[0132] Abnormal situation 2: If the switch operation status in the PMS system is inconsistent with the operation status in the D5200 system, the switch is recorded as abnormal operation status;

[0133] Traverse all switches and find out the abnormal operation status of each switch;

[0134] According to the abnormal operation status of each switch, two labels are divided: normal and abnormal;

[0135] Finally, all switches are labeled with operational status characteristics.

[0136] S2.8. Establish switch point table situation characteristic label: Combine the switch signal and measurement data to check the switch operation status and establish the switch point table situation status label, as follows:

[0137] Obtain the terminal ledger data of all switch maintenance, including terminal name, terminal model, and terminal mark. Combined with the remote signal and protection information sent by the switch, check whether the terminal information of the switch is correctly maintained. If so, the switch point table is normal, otherwise the switch point table is abnormal.

[0138] Finally, we get the point table status labels of all switches, which are divided into two types: normal and abnormal.

[0139] S2.9. Establishing the rationality status label of the switch hierarchical protection layout: By counting the number of downstream distribution variables of the automated switch, establish the rationality status label of the switch hierarchical protection layout; the details are as follows:

[0140] Combined with the topological connection relationship between the switch and the distribution transformer, calculate the number of distribution transformers downstream of the hierarchical protection switch, and judge the rationality of the hierarchical protection setting of the trunk line based on the number. If the number of distribution transformers downstream of the hierarchical protection switch does not reach 15, it is reasonable, otherwise it is unreasonable;

[0141] Finally, the layout rationality labels of all graded protection switches are obtained, which are divided into two types: reasonable and unreasonable.

[0142] S2.10. Establish a label for the rationality of switch hierarchical protection and FA coordination: By finding out whether there is a hierarchical protection switch in the fault area topologically upstream of the fault area determined by FA, ​​establish a label for the rationality of switch hierarchical protection and FA coordination; the details are as follows:

[0143] For switches with FA fault analysis and hierarchical protection functions, according to the fault starting point switch given in the FA area, check whether there is a hierarchical protection action switch in the upstream of the topology. If so, the coordination between hierarchical protection and FA is unreasonable. The labels of coordination between other switches and FA are reasonable by default.

[0144] Finally, we get the status labels of all switches that feel bad and cooperate with FA for rationality. There are two types of labels: reasonable and unreasonable.

[0145] S2.11. Establish the switch FA positioning fault interval accuracy status label: Establish the switch FA positioning fault interval accuracy label by finding whether the first switch of the fault area formed by the most downstream protection alarm switch is the first switch of the fault area located by FA in the topology upstream. The details are as follows:

[0146] Based on the protection alarm switch at the most downstream of the line, look upstream to see if there is a switch at the fault starting point given by the FA fault interval. If so, the suspected fault interval is expanded, and the accuracy of the FA fault interval is low. Otherwise, it is high:

[0147] Finally, the FA positioning fault interval accuracy status labels of all switches are obtained, which are divided into two types: higher and lower.

[0148] After completing the above steps, 11 feature labels can be established, including switch voltage measurement status, current measurement status, power measurement status, switch protection and opening and closing status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, and switch FA fault positioning accuracy status. Each label can be digitally mapped to prepare for the data input of the subsequent model.

[0149] S3. Model establishment: According to the extracted health status characteristics of each switch, the weight of each feature label item is obtained using the hierarchical analysis method, and a comprehensive evaluation model is established.

[0150] In this embodiment, the feature label data of the automation switch is integrated and extracted to form an evaluation sample set of the health status of the automation switch, the weight of each feature label item is obtained according to the hierarchical analysis method, and a comprehensive evaluation model is established.

[0151] This comprehensive evaluation model is a common evaluation model in the prior art, which mainly focuses on feature selection. Once the features are selected, the mature model can be directly applied.

[0152] S4. Health status assessment: Use a comprehensive evaluation model to conduct batch assessment of the health status of each automation switch.

[0153] In this embodiment, based on the obtained weights of each feature label item, batch generation of label item feature data is performed for each automation switch and the required feature value evaluation weight is calculated, which is sent to the comprehensive evaluation model for calculation, and finally the data health status evaluation result corresponding to each automation switch is output.

[0154] For example, if we conduct a batch health status assessment on the automated switch data of a district or county in a city for one day, the results are as follows:

[0155] Automatic switch health status Number of automatic switches Proportion Very low health 134 3％ Lower health 494 11％ Medium health 3318 74％ Higher health 539 12％ total 4485 /

[0156] We selected a switch with extremely low health and went to the site to inspect the terminal side. We found that the external wiring of the terminal was incorrect and the short-circuit of the current secondary circuit was connected incorrectly and was not disconnected, resulting in the secondary circuit not being connected to the primary circuit. There was no current flowing in the secondary circuit, causing the terminal current and power collection values ​​to be 0. After the short-circuit of the current secondary circuit was correctly connected, the current and power measurements of the automatic switch were sent normally.

[0157] In this case, based on the extremely low health label of the automation switch, local city personnel went to the site to check the automation switch, and finally located that the data sent by the switch was not collected due to the abnormal wiring method of the automation switch. After on-site adjustments, the data upload was normal, and the switch was then in an extremely high health label. It can be seen that this patent can be actually put into use to guide local cities to check and adjust automation switches with low health, forming an application closed loop.

[0158] The present invention is based on the data related to automation switches, and uses a comprehensive evaluation model to reasonably evaluate the health status of automation switches, helping to provide companies with available, usable and easy-to-use data.

[0159] Example 2

[0160] See also Figure 2 , Figure 2 The present invention discloses a structural diagram of a distribution network automation switch health status assessment system based on hierarchical comprehensive evaluation, which can implement health status assessment of multi-source data of distribution network automation switches, and specifically includes:

[0161] Data acquisition module, used to obtain the ledger and measurement data of lines, switches, distribution transformers, signal data sent by automatic switches, and records of line fault power outages, power transfers, and operation tickets;

[0162] The health status sub-item extraction module is used to extract health status features from the acquired data and label them with features, where the health status features include switch voltage measurement status, current measurement status, power measurement status, switch protection and opening and closing transmission status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, and switch FA positioning fault interval accuracy status;

[0163] The model building module is used to obtain the weight of each feature label item based on the extracted health status characteristics of each switch using the hierarchical analysis method and establish a comprehensive evaluation model;

[0164] The health status assessment module is used to batch assess the health status of each automation switch using a comprehensive evaluation model.

[0165] In an optional embodiment, a method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation includes: a) obtaining the ledgers and measurement data of lines, switches, and distribution transformers, the signal data sent by the automation switches, and the line fault power outage, transfer, and operation ticket records; b) extracting health status features and marking them with feature labels; c) using the hierarchical analysis method based on the extracted health status features of each switch to obtain the weight of each feature label item and establish a comprehensive evaluation model; d) using the comprehensive evaluation model to batch evaluate the health status of each automation switch.

[0166] Example 3

[0167] See also Figure 3 , Figure 3 The present invention discloses a schematic diagram of a device for evaluating the health status of a distribution network automation switch based on hierarchical comprehensive evaluation. Figure 3 The described device can be applied in power systems, such as for health status assessment of multi-source data of distribution network automation switches, etc., which is not limited in the embodiments of the present invention.

[0168] like Figure 3 As shown, the device may include a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method described in the above embodiment and can achieve the technical effect consistent with the above method.

[0169] The memory may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the memory may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). A program / utility having a set (at least one) of program modules may be stored in, for example, the memory, such program modules including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment. The program modules typically perform the functions and / or methods in the embodiments described herein.

[0170] The processor executes various functional applications and data processing by running the program stored in the memory, such as implementing the method provided in the first embodiment of the present invention.

[0171] Example 4

[0172] Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the above embodiment are implemented and the technical effect consistent with the above method can be achieved.

[0173] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0174] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0175] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0176] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0177] Of course, the storage medium containing computer executable instructions provided by an embodiment of the present invention, whose computer executable instructions are not limited to the above method operations, can also execute related operations in the method provided by any embodiment of the present invention.

[0178] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation, characterized in that: include: Data acquisition: obtain the ledger and measurement data of lines, switches, distribution transformers, signal data sent by automatic switches, and records of line failure power outages, power transfers, and operation tickets; Extraction of health status by item: Extract health status features from the acquired data and add feature labels, where health status features include switch voltage measurement status, current measurement status, power measurement status, switch protection and opening and closing transmission status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, switch FA positioning fault interval accuracy status; Model establishment: Based on the extracted health status characteristics of each switch, the weight of each feature label item is calculated using the hierarchical analysis method, and a comprehensive evaluation model is established; Health status assessment: Use a comprehensive evaluation model to conduct batch assessment of the health status of each automation switch.

2. The method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation according to claim 1 is characterized in that: The records and measurement data of the lines, switches and distribution transformers include the basic information of the lines, switches and distribution transformers maintained in the PMS system, marketing system and distribution automation system, the power measurement, power factor value, voltage measurement and current measurement data of the switches and distribution transformers, and the topological connection relationship data of the lines, switches and distribution transformers; The signal data sent by the automatic switch includes protection signals, opening and closing signals, FA fault areas, FA tests and switch listing information sent by all automatic switches in the distribution network of the distribution automation system; The line fault power outage, transfer, and operation ticket records include line fault information, line power outage related information in the power outage reliability system, packaged data information applied by the city and prefecture of the line loss system, and operation ticket records filled in by the city and prefecture.

3. The method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation according to claim 1 is characterized in that: Extract health status features from the acquired data and label them, including: By checking the missing and abnormal conditions of the automatic switch voltage measurement, the switch voltage measurement status characteristic label is established; By checking the missing and abnormal conditions of automatic switch current measurement, a switch current measurement status feature label is established; By checking the missing and abnormal conditions of the automatic switch power measurement, the switch power measurement status characteristic label is established; By checking the automatic switch action signal sent by the distribution automation system, the quality status characteristic label of the switch opening and closing signal is established; The automation switch type label status is established by verifying the consistency of the switch type maintained by the automation switch in the PMS system and the distribution automation system.

4. The method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation according to claim 1 is characterized in that: Extract health status features from the acquired data and label them, including: Combine the switch signal and measurement data to check the switch operation status, and establish two status characteristics: switch operation label status and switch point table status; By counting the number of downstream distribution variables of the automated switch, a rationality status label for the switch hierarchical protection layout is established.

5. The method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation according to claim 1 is characterized in that: Extract health status features from the acquired data and label them, including: By finding out whether there is a hierarchical protection switch in the topological upstream of the fault area identified by FA, ​​a status label of the rationality of the coordination between the hierarchical protection of the switch and FA is established; By finding out whether there is a first switch in the fault area located by FA in the topology upstream of the first switch in the fault area formed by the most downstream protection alarm switch, a switch FA location fault interval accuracy label is established.

6. The method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation according to claim 1 is characterized in that: According to the extracted health status characteristics of each switch, the weight of each feature label item is obtained using the hierarchical analysis method, and a comprehensive evaluation model is established, including: The feature label data of the automation switch is integrated and extracted to form an evaluation sample set for the health status of the automation switch. The weight of each feature label item is obtained according to the hierarchical analysis method, and a comprehensive evaluation model is established.

7. The method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation according to claim 6 is characterized in that: The comprehensive evaluation model is used to evaluate the health status of each automation switch in batches, including: Based on the obtained weights of each feature label item, batches of label item feature data are generated for each automation switch and the required feature value evaluation weights are calculated. The data are sent to the comprehensive evaluation model for calculation, and finally the data health status assessment results corresponding to each automation switch are output.

8. A distribution network automation switch health status assessment system based on hierarchical comprehensive evaluation, characterized in that: include: Data acquisition module, used to obtain the ledger and measurement data of lines, switches, distribution transformers, signal data sent by automatic switches, and records of line fault power outages, power transfers, and operation tickets; The health status sub-item extraction module is used to extract health status features from the acquired data and label them with features, where the health status features include switch voltage measurement status, current measurement status, power measurement status, switch protection and opening and closing transmission status, switch type label status, switch commissioning label status, switch point table status, switch hierarchical protection layout rationality status, switch hierarchical protection and FA coordination rationality status, and switch FA positioning fault interval accuracy status; The model building module is used to obtain the weight of each feature label item based on the extracted health status characteristics of each switch using the hierarchical analysis method and establish a comprehensive evaluation model; The health status assessment module is used to batch assess the health status of each automation switch using a comprehensive evaluation model.

9. A distribution network automation switch health status assessment device based on hierarchical comprehensive evaluation, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for evaluating the health status of distribution network automation switches based on hierarchical comprehensive evaluation as claimed in any one of claims 1 to 7.

Images