Microgrid equipment problem data processing method and system

Abstract

The present invention provides a method and system for processing data of microgrid equipment problems, and relates to data processing technology. The method includes counting the operation information of all microgrid equipment and performing a screening to obtain equipment to be diagnosed, classifying and counting the equipment to be diagnosed based on line association relationships and label association relationships, and obtaining multiple equipment association groups; locating the associated information of the associated equipment according to the preset training regression rules to obtain the dependent variable information group and the independent variable information group; and processing based on the regression algorithm to obtain the regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain the preliminary regression sub-coefficient; counting all the regression sub-coefficients of each equipment association group and inputting them into the fault diagnosis tree, extracting the normalization coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generating corresponding analysis results based on all the normalization coefficients. The actual operation conditions and associations between the equipment can be combined to automatically and effectively identify potential fault lines and equipment.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to a method and system for processing microgrid equipment problem data. Background Art

[0002] As an important form of distributed energy access to the grid, the problem of equipment failure in microgrids is becoming increasingly prominent. There are many types of microgrid equipment, including generators, transformers, circuit breakers, lines, etc. These devices may fail during operation due to aging, overload, short circuit and other reasons. Once a failure occurs, it will not only affect the normal operation of the microgrid, but may also pose a threat to the safety of the grid. Therefore, timely and accurate fault diagnosis of microgrid equipment is crucial.

[0003] In the prior art, the diagnosis of microgrid equipment failures mainly relies on manual inspections and regular testing. Manual inspections require professionals to conduct on-site inspections of the equipment, which is not only time-consuming and labor-intensive, but also difficult to detect potential faults. Although regular testing can regularly test the performance of the equipment, the testing cycle is long and cannot reflect the equipment status in real time. In addition, the fault diagnosis methods in the prior art often only target a single device, ignoring the correlation and mutual influence between devices, resulting in inaccurate and incomplete diagnostic results.

[0004] Therefore, how to combine the actual operating conditions and correlations between devices to automatically and effectively identify potential faulty lines and equipment has become an urgent problem to be solved. Summary of the invention

[0005] The embodiment of the present invention provides a method and system for processing microgrid equipment problem data, which can automatically and effectively identify potential faulty lines and equipment by combining the actual operating conditions and correlations between the equipment.

[0006] A first aspect of an embodiment of the present invention provides a method for processing microgrid equipment problem data, comprising:

[0007] The operation information of all microgrid devices is counted, and the devices to be diagnosed are screened based on the operation information. The devices to be diagnosed are classified and counted based on the line association relationship and the label association relationship to obtain multiple device association groups;

[0008] Extracting the associated devices and associated information corresponding to the device associated group, and locating the associated information of the associated devices according to the preset trained regression rules to obtain the dependent variable information group and the independent variable information group;

[0009] Processing the dependent variable information group and the independent variable information group based on a regression algorithm to obtain a regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain a preliminary regression sub-coefficient;

[0010] All regression sub-coefficients of each device association group are counted and input into the fault diagnosis tree, the normalized coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree are extracted, and corresponding analysis results are generated based on all the normalized coefficients.

[0011] Optionally, in a possible implementation of the first aspect, the operation information of all microgrid devices is counted, and the devices to be diagnosed are screened based on the operation information, and the devices to be diagnosed are classified and counted based on line association relationships and label association relationships to obtain multiple device association groups, including:

[0012] If it is determined that the operation information of the microgrid device meets the start-up conditions, the microgrid devices that meet the start-up conditions are screened out to obtain the devices to be diagnosed;

[0013] Obtaining a grid connection point of the microgrid, and performing reverse routing processing on a line to the microgrid based on the grid connection point to obtain a plurality of sub-lines;

[0014] The device to be diagnosed corresponding to each sub-line is determined as a first classification set with a line association relationship, and each first classification set is associated based on the label association relationship to obtain a device association group, and each label association relationship corresponds to at least two devices to be diagnosed.

[0015] Optionally, in a possible implementation manner of the first aspect, the acquiring a grid connection point of a microgrid device, and performing reverse routing processing on a microgrid based on the grid connection point to obtain a plurality of sub-lines include:

[0016] After obtaining the grid connection point of the microgrid device, the path search is performed in the reverse current direction. After determining that a branch appears at any line point in the path search, the corresponding line point is used as the branch point, and the line after the branch is searched again until the terminal microgrid device is reached;

[0017] Count the lines between each branch point and the adjacent branch points, terminal microgrid equipment or grid connection points to obtain branch lines;

[0018] If the length of the branch line is less than or equal to the first length, the corresponding branch line is used as a sub-line;

[0019] If the length of the branch line is greater than the first length, the branch line is evenly divided into a plurality of sub-lines.

[0020] Optionally, in a possible implementation manner of the first aspect, if the length of the branch line is greater than the first length, equally dividing the branch line to obtain a plurality of sub-lines includes:

[0021] Calculate the value of the branch line divided by the first length and round it up to obtain a first average value, and divide the branch line into equal parts based on the first average value to obtain a plurality of equal division points;

[0022] The branch line is equally divided according to the equally divided points to obtain a plurality of sub-lines.

[0023] Optionally, in a possible implementation manner of the first aspect, the determining the device to be diagnosed corresponding to each sub-line as a first classification set having a line association relationship, associating each first classification set based on a label association relationship to obtain a device association group, each label association relationship corresponding to at least two devices to be diagnosed, includes:

[0024] Acquire a preset association tree structure, wherein the association tree structure includes multiple levels of association nodes, each association node includes an association slot group, each association slot group corresponds to a plurality of different device slots, and the device slots of the connected lower-level association nodes completely include the device slots of the upper-level association nodes;

[0025] Sequentially traverse the device tags of each device to be diagnosed in the first classification set and fill them into the corresponding device slots;

[0026] After it is determined that all the devices to be diagnosed in the first classification set are filled, and the device tags are filled into all the device slots in the association tree structure, the associated slot group of each associated node is analyzed to obtain a device association group.

[0027] Optionally, in a possible implementation of the first aspect, after determining that all devices to be diagnosed in the first classification set are filled, and the device tags are filled into all device slots in the association tree structure, analyzing the associated slot group of each associated node to obtain a device association group includes:

[0028] Get the starting node and all the ending nodes in the associated tree structure, and connect the starting node with each ending node in sequence to obtain the corresponding structure tree path;

[0029] Following the direction of the structure tree path from the starting node to the ending node, the device labels in the associated slot group of each associated node are traversed in turn. If it is determined that all device slots in the associated slot group have device labels, the corresponding associated nodes are marked and new associated nodes are traversed again in the above direction until the associated nodes that serve as the ending nodes are traversed;

[0030] If it is determined that there is a device slot without a device label in the associated slot group, the corresponding associated node is used as the end point and no new associated nodes are traversed in the above direction;

[0031] The associated slot groups of all marked associated nodes are counted to obtain the device associated group.

[0032] Optionally, in a possible implementation manner of the first aspect, extracting the associated devices and associated information corresponding to the device association group, and locating the associated information of the associated devices according to a preset trained regression rule to obtain a dependent variable information group and an independent variable information group, includes:

[0033] Extracting the corresponding associated devices in the device association group, and obtaining at least one regression rule based on the corresponding relationship between the associated devices, each regression rule having target information of the corresponding associated device, and the target information having a dependent variable label or an independent variable label;

[0034] The associated information is screened and classified based on the dependent variable label or the independent variable label to obtain the dependent variable information group and the independent variable information group corresponding to each regression rule.

[0035] Optionally, in a possible implementation manner of the first aspect, the processing of the dependent variable information group and the independent variable information group based on the regression algorithm to obtain a regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain a preliminary regression sub-coefficient includes:

[0036] Based on the regression algorithm, the dependent variable information group and the independent variable information group are processed as output and input respectively to obtain the regression coefficient;

[0037] If the regression coefficient corresponds to the fault coefficient in the fault diagnosis coefficient, it represents the preliminary regression sub-coefficient of the fault;

[0038] If the regression coefficient does not correspond to the fault coefficient in the fault diagnosis coefficient, it indicates a preliminary regression sub-coefficient of non-fault.

[0039] Optionally, in a possible implementation manner of the first aspect, counting all regression sub-coefficients of each device association group and inputting them into a fault diagnosis tree, extracting normalized coefficients of the regression sub-coefficients of nodes in the fault diagnosis tree, and generating corresponding analysis results based on all normalized coefficients, including:

[0040] The fault diagnosis tree includes sub-fault nodes and comprehensive result nodes, and each sub-fault node corresponds to an associated node of a device associated group;

[0041] Each sub-fault node is normalized according to fault and non-fault based on the regression sub-coefficient of the corresponding device association group to obtain a normalized coefficient;

[0042] Each comprehensive result node is connected to at least a plurality of sub-fault nodes, and each comprehensive result node performs calculation combination based on the normalized coefficients of the plurality of sub-fault nodes to obtain an analysis result, and different calculation combinations correspond to different analysis results.

[0043] Optionally, in a possible implementation manner of the first aspect, each comprehensive result node is connected to at least a plurality of sub-fault nodes, and each comprehensive result node performs calculation combination based on normalization coefficients of the plurality of sub-fault nodes to obtain an analysis result, and different calculation combinations correspond to different analysis results, including:

[0044] If it is determined that the corresponding comprehensive result node has other comprehensive result nodes in the upper dimension, the other comprehensive result nodes are taken as the first containing nodes, and other comprehensive result nodes at the same level as the corresponding comprehensive result node in the lower dimension of the first containing node are determined as contained nodes;

[0045] The normalized coefficients of the corresponding comprehensive result nodes and the included nodes at the same level are calculated and combined to obtain the analysis result of the first included node.

[0046] A second aspect of an embodiment of the present invention provides a microgrid equipment problem data processing system, comprising:

[0047] A statistical module is used to collect statistics on the operation information of all microgrid devices, screen the devices to be diagnosed based on the operation information, classify and count the devices to be diagnosed based on the line association relationship and label association relationship, and obtain multiple device association groups;

[0048] An extraction module is used to extract the associated devices and associated information corresponding to the device association group, and locate the associated information of the associated devices according to the preset training regression rules to obtain the dependent variable information group and the independent variable information group;

[0049] A processing module, used for processing the dependent variable information group and the independent variable information group based on a regression algorithm to obtain a regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain a preliminary regression sub-coefficient;

[0050] The generation module is used to count all regression sub-coefficients of each device association group and input them into the fault diagnosis tree, extract the normalization coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generate corresponding analysis results based on all the normalization coefficients.

[0051] According to a third aspect of an embodiment of the present invention, a storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the method of the first aspect of the present invention and various possible designs of the first aspect.

[0052] The beneficial effects of the present invention are as follows:

[0053] 1. The present invention can efficiently and accurately screen out the microgrid equipment to be diagnosed, and classify and count them based on the line association relationship and the label association relationship to form multiple equipment association groups. This process not only simplifies the complexity of fault diagnosis, but also improves the pertinence of diagnosis. First, by counting and analyzing the operating information of microgrid equipment, it is possible to quickly identify equipment that is in operation and may have faults, avoiding invalid operations on equipment that does not require diagnosis. Secondly, based on the association relationship between lines and labels, the equipment is classified and counted, which helps to more comprehensively consider the mutual influence and correlation between equipment in subsequent fault diagnosis, thereby improving the accuracy and comprehensiveness of the diagnostic results. The implementation of this series of steps has laid a solid foundation for subsequent fault diagnosis work.

[0054] 2. The present invention obtains the dependent variable information group and the independent variable information group by extracting the associated devices and their associated information in the device association group and locating the information based on the preset trained regression rules. The implementation of this step enables the fault diagnosis process to make full use of the operating data and correlation information between the devices, further improving the accuracy of the diagnosis. The dependent variable and independent variable information groups are processed by the regression algorithm to obtain the regression coefficient, which is compared with the fault diagnosis coefficient to preliminarily determine whether the equipment has a fault. This process not only realizes the rapid identification of equipment faults, but also reduces the subjectivity and uncertainty of manual judgment, and improves the objectivity and accuracy of diagnosis.

[0055] 3. The present invention achieves in-depth analysis and comprehensive presentation of fault diagnosis results by counting all regression sub-coefficients of each device association group and inputting them into the fault diagnosis tree. In the fault diagnosis tree, each sub-fault node corresponds to an associated node of the device association group, and a normalized coefficient can be obtained based on the normalization processing of the regression sub-coefficient. Furthermore, each comprehensive result node is calculated and combined based on the normalization coefficients of multiple sub-fault nodes to obtain different analysis results. This process not only makes the fault diagnosis results more intuitive and easy to understand, but also facilitates the location and cause analysis of the fault, providing strong support for subsequent fault handling and maintenance. At the same time, the method of the present invention also has good scalability and flexibility, and can adapt to the fault diagnosis needs of microgrid equipment of different scales and complexities. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 The present invention provides a flow chart of a method for processing microgrid equipment problem data.

[0057] Figure 2 This is a structural schematic diagram of a microgrid equipment problem data processing system provided by the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0059] See also Figure 1 , is a flow chart of a method for processing microgrid device problem data provided by an embodiment of the present invention, the method comprising steps S1-S4:

[0060] S1, counting the operation information of all microgrid devices, performing a screening based on the operation information to obtain the devices to be diagnosed, classifying and counting the devices to be diagnosed based on the line association relationship and the label association relationship, and obtaining multiple device association groups.

[0061] It should be noted that microgrid is called microgrid, which refers to a small power generation and distribution system composed of distributed power sources, energy storage devices, energy conversion devices, loads, monitoring and protection devices, etc. For example, the power grid composed of photovoltaic, wind power and other energy sources corresponding to distributed power sources is a microgrid, and then the current generated by the microgrid is input into the city power network through the grid connection point.

[0062] Therefore, microgrid equipment can be equipment before the grid connection point, such as solar photovoltaic cells, wind turbines, etc.

[0063] Specifically, the server will perform a screening based on the operation information of the microgrid equipment to obtain the equipment to be diagnosed, and will classify and count the equipment to be diagnosed based on the line association relationship and the label association relationship to obtain multiple equipment association groups.

[0064] In some embodiments, step S1 (counting the operation information of all microgrid devices, performing a screening based on the operation information to obtain devices to be diagnosed, and classifying and counting the devices to be diagnosed based on line association relationships and tag association relationships to obtain multiple device association groups) includes steps S11-S13:

[0065] S11, if it is determined that the operation information of the microgrid device meets the start-up conditions, the microgrid devices that meet the start-up conditions are screened out to obtain the devices to be diagnosed.

[0066] The operation information is the operating status information of the microgrid equipment, and the start-up condition is the operating condition.

[0067] It is not difficult to understand that if the microgrid equipment is not in operation, the corresponding signal parameters will not be output, so comparative calculations cannot be performed, and diagnosis is meaningless.

[0068] Therefore, if it is determined that the operating information of the microgrid device meets the startup conditions, that is, the microgrid device is in operation, the microgrid devices in operation are selected as devices to be diagnosed, thereby facilitating the subsequent judgment of whether the operating status of the devices to be diagnosed is normal.

[0069] S12, obtaining a grid connection point of the microgrid, and performing reverse routing processing on the microgrid based on the grid connection point to obtain a plurality of sub-lines.

[0070] Among them, the grid connection point is the point where the grid is connected to the mains circuit.

[0071] It should be noted that a microgrid is a power grid composed of multiple devices and has multiple sub-lines. Therefore, during subsequent diagnosis, the devices on the same sub-line will be counted, and then it can be determined whether there is a problem with the line based on the association relationship between the devices on the same line.

[0072] Therefore, the server will obtain the grid connection point of the microgrid, and perform reverse routing processing on the line to the microgrid based on the grid connection point to obtain multiple sub-lines.

[0073] Through the above implementation, the microgrid can be divided into multiple sub-circuits, which facilitates the subsequent classification of related devices.

[0074] In some embodiments, step S12 (obtaining a grid connection point of a microgrid device, and performing reverse routing processing on a microgrid based on the grid connection point to obtain a plurality of sub-lines) includes S121-S124:

[0075] S121, after obtaining the grid connection point of the microgrid device, the path search is performed in the reverse current direction. After determining that a branch appears at any line point in the path search, the corresponding line point is used as the branch point, and the line after the branch is path searched again until the terminal microgrid device is reached.

[0076] It should be noted that the normal current direction is the direction of the current input to the grid connection point, therefore, the reverse current direction is from the grid connection point to the microgrid, which facilitates the subsequent reverse determination of multiple sub-circuits in the microgrid.

[0077] The reverse current direction is the direction opposite to the current, and the line point is the connection point of the line in the microgrid.

[0078] It can be understood that after the server obtains the grid connection point of the microgrid device, it will perform routing processing in the reverse direction of the current. If it is determined that a branch appears at any line point during the routing process, the corresponding line point will be used as the branch point, that is, a forked line appears at this line point. At this time, the line point will be used as the branch point, and the line after the branch will be routed again. When the line point after the branch appears again, it will be used as the branch point again until it reaches the terminal microgrid device, that is, the current path is traversed continuously in the opposite direction of the current until the terminal microgrid device is traversed, that is, all the microgrid devices are traversed and the traversal is completed.

[0079] S122, counting the lines between each branch point and adjacent branch points, terminal microgrid equipment or grid connection points to obtain branch lines.

[0080] It is not difficult to understand that the lines between each branch point and the adjacent branch points, terminal microgrid devices or grid connection points are counted to obtain branch lines. That is, in the reverse current direction, the server will regard the lines between the adjacent branch points, terminal microgrid devices or grid connection points in the direction as branch lines.

[0081] For example, the grid connection point is connected to a line, which is then divided into two lines through a branch point. The branch line is the line between the grid connection point and the branch point, and the line corresponding to the branch point and the terminal microgrid device is the branch line.

[0082] S123: If the length of the branch line is less than or equal to the first length, use the corresponding branch line as a sub-line.

[0083] It should be noted that if the branch line is too long, it means that there are many corresponding devices on the branch line. When the abnormality is analyzed and located later, it is not convenient to directly locate the abnormal part. Therefore, when the branch line is too long, the present invention will subsequently split the branch line. If the length meets the requirements, the line will be directly used as a sub-line.

[0084] The first length may be a length preset manually.

[0085] It can be understood that if the length of the branch line is less than or equal to the first length, the corresponding branch line is used as a sub-line.

[0086] S124: If the length of the branch line is greater than the first length, equally divide the branch line into a plurality of sub-lines.

[0087] It is understandable that if the length of the branch line is greater than the first length, it means that the branch line is too long, and therefore, the branch line will be evenly divided into multiple sub-lines.

[0088] In some embodiments, step S124 (if the length of the branch line is greater than the first length, the branch line is evenly divided into multiple sub-lines) includes S1241-S1242:

[0089] S1241, calculating the value of the branch line divided by the first length and rounding up to obtain a first average value, and dividing the branch line into equal parts based on the first average value to obtain a plurality of equal division points.

[0090] It is understandable that the server will calculate the length of the branch line divided by the value of the first length, and round it up to obtain the first average value. For example, if the calculated value is 2.5, the first average value after rounding up is 3.

[0091] Specifically, the branch line is subsequently divided equally according to the first equal division value to obtain a plurality of equally divided points. For example, if the first equal division value is 3, the branch line is divided into 3 equally, thereby obtaining 2 equally divided points.

[0092] S1242, acquiring the lines between all adjacent equally divided points to obtain a plurality of sub-lines corresponding to the branch lines.

[0093] It is understandable that the server will obtain the lines between all adjacent equally divided points to obtain multiple sub-lines corresponding to the branch lines. That is, after the equally divided branch lines are processed, multiple sub-lines can be obtained.

[0094] S13, determining the devices to be diagnosed corresponding to each sub-line as a first classification set with a line association relationship, and associating each first classification set based on the label association relationship to obtain a device association group, wherein each label association relationship corresponds to at least two devices to be diagnosed.

[0095] It should be noted that there is a functional relationship between the devices located in the same sub-line and the power parameters. If the functional relationship is normal, it means that there is no problem with the devices on the line. If the functional relationship is abnormal, it means that there is a problem with the devices on the line.

[0096] Therefore, the server will count the devices to be diagnosed corresponding to each sub-line as the first classification set with line association relationship, so the line association relationship is the relationship on the same sub-line.

[0097] Subsequently, the server will associate each first classification set based on the tag association relationship to obtain a device association group, each tag association relationship corresponds to at least two devices to be diagnosed, that is, the server will subsequently associate based on the association relationship between the device tags on the sub-line to obtain a device association group.

[0098] In some embodiments, step S13 (determining the device to be diagnosed corresponding to each sub-line as a first classification set having a line association relationship, associating each first classification set based on the tag association relationship to obtain a device association group, and each tag association relationship corresponds to at least two devices to be diagnosed) includes S131-S133:

[0099] S131, obtaining a preset association tree structure, wherein the association tree structure includes multiple levels of association nodes, each association node includes an association slot group, each association slot group corresponds to a plurality of different device slots, and the device slots of the connected lower-level association nodes completely include the device slots of the upper-level association nodes.

[0100] Among them, the preset association tree structure is an association tree structure set in advance by humans, which can be a structure tree set in advance based on the connection relationship between sub-circuits in the microgrid. The association tree structure is composed of multiple levels of association nodes, and the association nodes are nodes in the tree structure. For example, it can be a multi-level tree node such as a parent node, a child node, and a grandchild node, and each association node is generated based on the sub-circuit.

[0101] Among them, each associated node has a corresponding associated slot group, and each associated slot group corresponds to multiple different device slots. For example, there are 5 devices on a sub-line, but only 3 of them are associated. At this time, the associated slot group corresponding to the associated node has 3 associated device slots, that is, the associated slot group corresponding to the associated node is pre-set according to the association relationship of the devices on each sub-line.

[0102] Subsequently, the device slots of the lower level associated nodes connected to the associated node completely include the device slots of the upper level associated nodes. For example, the associated slot group corresponding to the associated node 2 has three associated device slots (slot A, slot B, and slot C), then the device slots of the lower level associated nodes connected to the associated node 2 (slot A, slot B, slot C, slot D, and slot E), that is, completely include slot A, slot B, and slot C.

[0103] S132, traversing the device tags of each device to be diagnosed in the first classification set in turn and filling them into the corresponding device slots.

[0104] The first classification set is a set consisting of all devices to be diagnosed that are in operation on each sub-line.

[0105] It can be understood that the server sequentially traverses the device tag of each device to be diagnosed in the first classification set corresponding to the sub-line of each associated node and fills it into the corresponding device slot.

[0106] Through the above implementation, the devices to be diagnosed in the remote state on each sub-line are filled into the position of the associated node corresponding to the sub-line.

[0107] S133, after it is determined that all the devices to be diagnosed in the first classification set have been filled, and the device tags have been filled into all the device slots in the association tree structure, the associated slot group of each associated node is analyzed to obtain a device association group.

[0108] It can be understood that after it is determined that all the devices to be diagnosed in the first classification set are filled, that is, after all the running devices to be diagnosed on all sub-lines are filled, and the corresponding device tags are filled into the corresponding device slots in the association tree structure, the associated slot group of each associated node is analyzed to obtain the device association group.

[0109] In some embodiments, step S133 (after determining that all devices to be diagnosed in the first classification set have been filled, and the device tags have been filled into all device slots in the association tree structure, analyzing the associated slot group of each associated node to obtain a device association group) includes S1331-S1334:

[0110] S1331, obtaining the starting node and all the ending nodes in the associated tree structure, and sequentially connecting the starting node with each ending node to obtain a corresponding structure tree path.

[0111] The starting node is the starting associated node, such as a parent node; the ending node is the ending associated node, such as a grandchild node.

[0112] It is understandable that the server will obtain the starting node and all the ending nodes in the associated tree structure, and connect the starting node with each ending node in sequence to obtain the corresponding structure tree path, that is, the structure path from the parent node to each grandchild node.

[0113] S1332, traverse the device labels in the associated slot group of each associated node in turn according to the direction from the starting node to the ending node of the structure tree path. If it is determined that all device slots in the associated slot group have device labels, mark the corresponding associated nodes and traverse the new associated nodes again in the above direction until the associated node that serves as the ending node is traversed.

[0114] It can be understood that the server traverses the device tags in the associated slot group of each associated node in turn along the structure tree path from the starting node to the ending node. If it is determined that all device slots in the associated slot group have device tags, it means that the devices associated with the associated node are all in operation, and the associated slot group corresponding to the associated node can be diagnosed for device association. Subsequently, the associated node is marked and the new associated node is traversed again in the above direction until the associated node serving as the ending node is traversed.

[0115] S1333: If it is determined that the associated slot group has a device slot without a device tag, the corresponding associated node is used as a cutoff point and no new associated nodes are traversed in the above direction.

[0116] It is understandable that if it is determined that there is a device slot without a device label in the associated slot group, it means that the device slot exists, but the device corresponding to the device slot is not in operation. For example, slot A, slot B and slot C correspond to devices A, device B and device C, but currently only devices A and device B are in operation. Therefore, devices A and device B are filled into the device slots. To analyze whether the line is abnormal, the data of the three devices with an associated relationship must be processed. Therefore, when only devices A and B are in operation, the line cannot be analyzed for faults, and subsequent sub-lines cannot be analyzed for faults. Therefore, the corresponding associated node is used as the end point and no new associated nodes are traversed in the above direction.

[0117] S1334, counting the associated slot groups of all marked associated nodes to obtain a device associated group.

[0118] It is understandable that the server will count the device tags in the associated slot groups corresponding to all marked associated nodes, thereby obtaining the device association groups corresponding to each associated node.

[0119] Through the above implementation, the present invention can improve processing efficiency and quickly determine which devices are related in the operation scenario, thereby performing fault diagnosis and analysis on the corresponding sub-routes.

[0120] S2, extracting the associated devices and associated information corresponding to the device associated group, and locating the associated information of the associated devices according to the preset trained regression rules to obtain a dependent variable information group and an independent variable information group.

[0121] It is understandable that the server will extract the corresponding associated devices and associated information in the device association group, and locate the associated information of the associated devices according to the preset trained regression rules to obtain the dependent variable information group and the independent variable information group.

[0122] In some embodiments, step S2 (extracting the associated devices and associated information corresponding to the device association group, and locating the associated information of the associated devices according to the preset trained regression rules to obtain the dependent variable information group and the independent variable information group) includes S21-S22:

[0123] S21, extracting the corresponding associated devices in the device association group, and obtaining at least one regression rule based on the corresponding relationship between the associated devices, each regression rule having target information of the corresponding associated device, and the target information having a dependent variable label or an independent variable label.

[0124] It is understandable that the server will extract the corresponding associated devices in the device association group, and obtain at least one regression rule based on the corresponding relationship between the associated devices. For example, three devices are associated with each other, and they have at least one regression rule.

[0125] Each regression rule has target information of the corresponding associated device, that is, the corresponding dependent variable label or independent variable label will always be extracted from different associated devices.

[0126] It is understandable that a device has a lot of information, such as voltage information, current information, etc. The first regression rule may require voltage information, and the next time may require current information. Among them, the associated information is the parameter information of the associated device in the regression rule, such as voltage, current, etc.

[0127] S22, screening and classifying the associated information based on the dependent variable label or the independent variable label to obtain a dependent variable information group and an independent variable information group corresponding to each regression rule.

[0128] It is understandable that the server will filter and classify the associated information of each device based on the dependent variable label or the independent variable label. In this way, the parameters of the dependent variable and the independent variable in each associated device can be grouped.

[0129] Specifically, the corresponding dependent variable group and independent variable information group may be determined according to the regression rules of the corresponding associated devices in the device association group, that is, each regression rule has a corresponding dependent variable group and independent variable information group.

[0130] Through the above implementation, the dependent variables and independent variables of each device are first grouped, and then grouped according to various regression rules, so as to facilitate subsequent calculations through regression algorithms.

[0131] S3, based on the regression algorithm, the dependent variable information group and the independent variable information group are processed to obtain regression coefficients, and the regression coefficients are compared with the fault diagnosis coefficients to obtain preliminary regression sub-coefficients.

[0132] It is understandable that the server will calculate and process the dependent variable information group and the independent variable information group based on the regression algorithm to obtain the regression coefficient, and compare the regression coefficient with the fault diagnosis coefficient to obtain the preliminary regression sub-coefficient.

[0133] In some embodiments, step S3 (processing the dependent variable information group and the independent variable information group based on the regression algorithm to obtain the regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain the preliminary regression sub-coefficient) includes S31-S33:

[0134] S31, based on the regression algorithm, the dependent variable information group and the independent variable information group are processed as output and input respectively to obtain the regression coefficient.

[0135] It should be noted that the dependent variable information group and the independent variable information group corresponding to the marked associated nodes have a certain proportional relationship. For example, the server inputs a group of dependent variable information groups and a group of independent variable information groups to obtain a k value. If this k value is normal, it means that the line is normal. If the k value is abnormal, it means that the line is abnormal, that is, the regression algorithm. This is the prior art and will not be elaborated here.

[0136] Therefore, based on the regression algorithm, the dependent variable information group and the independent variable information group are processed as input and output respectively to obtain the regression coefficient, that is, the corresponding k value coefficient can be obtained after calculation, and then the value is compared with the abnormal fault coefficient to determine whether there is a fault.

[0137] S32: If the regression coefficient corresponds to the fault coefficient in the fault diagnosis coefficient, it indicates a preliminary regression sub-coefficient of the fault.

[0138] It is understandable that if the regression coefficient corresponds to the fault coefficient in the fault diagnosis coefficient, it indicates a preliminary regression sub-coefficient of the fault. It is not difficult to understand that if it corresponds, it means that the line is faulty, and the regression coefficient is a preliminary regression sub-coefficient indicating the fault.

[0139] S33, if the regression coefficient does not correspond to the fault coefficient in the fault diagnosis coefficient, it indicates a preliminary regression sub-coefficient of non-fault.

[0140] It is understandable that if the regression coefficient does not correspond to the fault coefficient in the fault diagnosis coefficient, it indicates a preliminary regression sub-coefficient of non-fault. It is not difficult to understand that if there is no correspondence, it means that the line is not faulty, and the regression coefficient is a preliminary regression sub-coefficient indicating non-fault.

[0141] S4, counting all regression sub-coefficients of each device association group and inputting them into the fault diagnosis tree, extracting normalized coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generating corresponding analysis results based on all normalized coefficients.

[0142] It is understandable that the server will count all regression sub-coefficients of each device association group and input them into the fault diagnosis tree, extract the normalized coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generate corresponding analysis results based on all the normalized coefficients.

[0143] In some embodiments, step S4 (counting all regression sub-coefficients of each device association group and inputting them into the fault diagnosis tree, extracting normalized coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generating corresponding analysis results based on all normalized coefficients) includes S41-S43:

[0144] S41, the fault diagnosis tree includes sub-fault nodes and comprehensive result nodes, and each sub-fault node corresponds to an associated node of a device associated group.

[0145] It can be understood that the fault diagnosis tree includes sub-fault nodes and comprehensive result nodes, and each sub-fault node corresponds to an associated node of a device associated group.

[0146] Therefore, the server will connect the corresponding sub-fault nodes with the comprehensive result nodes according to the relationship between the associated nodes in the structure tree path corresponding to the associated tree structure, that is, connect the sub-fault nodes corresponding to multiple sub-lines on the same branch line with the corresponding comprehensive result nodes. Moreover, if multiple branch lines have branch lines connected to them in common, then multiple corresponding comprehensive result nodes can be connected to one comprehensive result node in common.

[0147] S42, each sub-fault node is normalized according to fault and non-fault based on the regression sub-coefficient of the corresponding device association group to obtain a normalized coefficient.

[0148] It can be understood that each sub-fault node is normalized according to fault and non-fault based on the regression sub-coefficient of the corresponding device association group to obtain a normalized coefficient.

[0149] S43, each comprehensive result node is connected to at least a plurality of sub-fault nodes, and each comprehensive result node performs calculation combination based on the normalized coefficients of the plurality of sub-fault nodes to obtain an analysis result, and different calculation combinations correspond to different analysis results.

[0150] In some embodiments, step S43 (each comprehensive result node is connected to at least a plurality of sub-fault nodes, each comprehensive result node performs calculation combination based on the normalized coefficients of the plurality of sub-fault nodes to obtain an analysis result, and different calculation combinations correspond to different analysis results) includes S431-S432:

[0151] S431, if it is determined that the corresponding comprehensive result node has other comprehensive result nodes in the upper dimension, the other comprehensive result nodes are used as the first including nodes, and other comprehensive result nodes at the same level as the corresponding comprehensive result node in the lower dimension of the first including node are determined as included nodes.

[0152] It can be understood that if it is determined that the corresponding comprehensive result node has other comprehensive result nodes in the upper dimension, the other comprehensive result nodes will be used as the first including nodes, and other comprehensive result nodes at the same level as the corresponding comprehensive result node in the lower dimension of the first including node will be determined as included nodes.

[0153] S432, statistically analyzing the normalized coefficients of the corresponding comprehensive result nodes and the included nodes at the same level, and performing calculation and combination to obtain the analysis result of the first included node.

[0154] It is not difficult to understand that the normalized coefficients of the corresponding comprehensive result nodes and the included nodes at the same level are calculated and combined to obtain the analysis result of the first included node.

[0155] Through the above method, it is possible to quickly locate whether there is a problem with the corresponding line or the equipment on the line, so as to discover the fault in time.

[0156] See also Figure 2 , is a schematic diagram of the structure of a microgrid device problem data processing system provided by an embodiment of the present invention, the microgrid device problem data processing system comprising:

[0157] A statistical module is used to collect statistics on the operation information of all microgrid devices, screen the devices to be diagnosed based on the operation information, classify and count the devices to be diagnosed based on the line association relationship and label association relationship, and obtain multiple device association groups;

[0158] An extraction module is used to extract the associated devices and associated information corresponding to the device association group, and locate the associated information of the associated devices according to the preset training regression rules to obtain the dependent variable information group and the independent variable information group;

[0159] A processing module, used for processing the dependent variable information group and the independent variable information group based on a regression algorithm to obtain a regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain a preliminary regression sub-coefficient;

[0160] The generation module is used to count all regression sub-coefficients of each device association group and input them into the fault diagnosis tree, extract the normalization coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generate corresponding analysis results based on all the normalization coefficients.

[0161] The present invention also provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the various embodiments described above.

[0162] Among them, the storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, the storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the storage medium can also exist in a communication device as discrete components. The storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0163] The present invention also provides a program product, which includes an execution instruction, which is stored in a storage medium. At least one processor of a device can read the execution instruction from the storage medium, and at least one processor executes the execution instruction so that the device implements the methods provided in the above various embodiments.

[0164] In the above-mentioned terminal or server embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing microgrid equipment problem data, characterized in that: include: The operation information of all microgrid devices is counted, and the devices to be diagnosed are screened based on the operation information. The devices to be diagnosed are classified and counted based on the line association relationship and the label association relationship to obtain multiple device association groups; Extracting the associated devices and associated information corresponding to the device associated group, and locating the associated information of the associated devices according to the preset trained regression rules to obtain the dependent variable information group and the independent variable information group; Processing the dependent variable information group and the independent variable information group based on a regression algorithm to obtain a regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain a preliminary regression sub-coefficient; Based on the regression algorithm, the dependent variable information group and the independent variable information group are processed as output and input respectively to obtain the regression coefficient; If the regression coefficient corresponds to the fault coefficient in the fault diagnosis coefficient, it represents the preliminary regression sub-coefficient of the fault; If the regression coefficient does not correspond to the fault coefficient in the fault diagnosis coefficient, it indicates a preliminary regression sub-coefficient of non-fault; All regression sub-coefficients of each device association group are counted and input into the fault diagnosis tree, the normalized coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree are extracted, and corresponding analysis results are generated based on all the normalized coefficients.

2. The microgrid equipment problem data processing method according to claim 1 is characterized in that: The operation information of all microgrid devices is counted, and the devices to be diagnosed are screened based on the operation information. The devices to be diagnosed are classified and counted based on the line association relationship and the label association relationship to obtain multiple device association groups, including: If it is determined that the operation information of the microgrid device meets the start-up conditions, the microgrid devices that meet the start-up conditions are screened out to obtain the devices to be diagnosed; Obtaining a grid connection point of the microgrid, and performing reverse routing processing on a line to the microgrid based on the grid connection point to obtain a plurality of sub-lines; The device to be diagnosed corresponding to each sub-line is determined as a first classification set with a line association relationship, and each first classification set is associated based on the label association relationship to obtain a device association group, and each label association relationship corresponds to at least two devices to be diagnosed.

3. The microgrid equipment problem data processing method according to claim 2 is characterized in that: The obtaining of the grid connection point of the microgrid device and performing reverse routing processing on the microgrid based on the grid connection point to obtain multiple sub-lines include: After obtaining the grid connection point of the microgrid device, the path search is performed in the reverse current direction. After determining that a branch appears at any line point in the path search, the corresponding line point is used as the branch point, and the line after the branch is searched again until the terminal microgrid device is reached; Count the lines between each branch point and the adjacent branch points, terminal microgrid equipment or grid connection points to obtain branch lines; If the length of the branch line is less than or equal to the first length, the corresponding branch line is used as a sub-line; If the length of the branch line is greater than the first length, the branch line is evenly divided into a plurality of sub-lines.

4. The microgrid equipment problem data processing method according to claim 3 is characterized in that: If the length of the branch line is greater than the first length, the branch line is evenly divided into multiple sub-lines, including: Calculate the value of the branch line divided by the first length and round it up to obtain a first average value, and divide the branch line into equal parts based on the first average value to obtain a plurality of equal division points; The branch line is equally divided according to the equally divided points to obtain a plurality of sub-lines.

5. The microgrid equipment problem data processing method according to claim 2 is characterized in that: The step of determining the device to be diagnosed corresponding to each sub-line as a first classification set having a line association relationship, and associating each first classification set based on the label association relationship to obtain a device association group, wherein each label association relationship corresponds to at least two devices to be diagnosed, includes: Acquire a preset association tree structure, wherein the association tree structure includes multiple levels of association nodes, each association node includes an association slot group, each association slot group corresponds to a plurality of different device slots, and the device slots of the connected lower-level association nodes completely include the device slots of the upper-level association nodes; Traverse the device tags of each device to be diagnosed in the first classification set in turn and fill them into the corresponding device slots; After it is determined that all the devices to be diagnosed in the first classification set are filled, and the device tags are filled into all the device slots in the association tree structure, the associated slot group of each associated node is analyzed to obtain a device association group.

6. The microgrid equipment problem data processing method according to claim 5 is characterized in that: After determining that all the devices to be diagnosed in the first classification set have been filled, and the device tags are filled into all the device slots in the association tree structure, analyzing the associated slot group of each associated node to obtain a device association group includes: Get the starting node and all the ending nodes in the associated tree structure, and connect the starting node with each ending node in sequence to obtain the corresponding structure tree path; Following the direction of the structure tree path from the starting node to the ending node, the device labels in the associated slot group of each associated node are traversed in turn. If it is determined that all device slots in the associated slot group have device labels, the corresponding associated nodes are marked and new associated nodes are traversed again in the above direction until the associated nodes that serve as the ending nodes are traversed; If it is determined that there is a device slot without a device label in the associated slot group, the corresponding associated node is used as the end point and no new associated nodes are traversed in the above direction; The associated slot groups of all marked associated nodes are counted to obtain the device associated group.

7. The microgrid equipment problem data processing method according to claim 1 is characterized in that: The extracting the associated devices and associated information corresponding to the device associated group, and locating the associated information of the associated devices according to the preset trained regression rules to obtain the dependent variable information group and the independent variable information group, includes: Extracting the corresponding associated devices in the device association group, and obtaining at least one regression rule based on the corresponding relationship between the associated devices, each regression rule having target information of the corresponding associated device, and the target information having a dependent variable label or an independent variable label; The associated information is screened and classified based on the dependent variable label or the independent variable label to obtain the dependent variable information group and the independent variable information group corresponding to each regression rule.

8. The microgrid equipment problem data processing method according to claim 1 is characterized in that: The method comprises: counting all regression sub-coefficients of each device association group and inputting them into the fault diagnosis tree, extracting normalized coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generating corresponding analysis results based on all normalized coefficients, including: The fault diagnosis tree includes sub-fault nodes and comprehensive result nodes, and each sub-fault node corresponds to an associated node of a device associated group; Each sub-fault node is normalized according to fault and non-fault based on the regression sub-coefficient of the corresponding device association group to obtain a normalized coefficient; Each comprehensive result node is connected to at least a plurality of sub-fault nodes, and each comprehensive result node performs calculation combination based on the normalized coefficients of the plurality of sub-fault nodes to obtain an analysis result, and different calculation combinations correspond to different analysis results.

9. The method for processing microgrid equipment problem data according to claim 8, characterized in that: Each comprehensive result node is connected to at least a plurality of sub-fault nodes. Each comprehensive result node performs calculation combination based on the normalized coefficients of the plurality of sub-fault nodes to obtain an analysis result. Different calculation combinations correspond to different analysis results, including: If it is determined that the corresponding comprehensive result node has other comprehensive result nodes in the upper dimension, the other comprehensive result nodes are taken as the first containing nodes, and other comprehensive result nodes at the same level as the corresponding comprehensive result node in the lower dimension of the first containing node are determined as contained nodes; The normalized coefficients of the corresponding comprehensive result nodes and the included nodes at the same level are calculated and combined to obtain the analysis result of the first included node.

10. Microgrid equipment problem data processing system, characterized in that: include: A statistical module is used to collect statistics on the operation information of all microgrid devices, screen the devices to be diagnosed based on the operation information, classify and count the devices to be diagnosed based on the line association relationship and label association relationship, and obtain multiple device association groups; An extraction module is used to extract the associated devices and associated information corresponding to the device association group, and locate the associated information of the associated devices according to the preset training regression rules to obtain the dependent variable information group and the independent variable information group; A processing module, used for processing the dependent variable information group and the independent variable information group based on a regression algorithm to obtain a regression coefficient, and comparing the regression coefficient with the fault diagnosis coefficient to obtain a preliminary regression sub-coefficient; Based on the regression algorithm, the dependent variable information group and the independent variable information group are processed as output and input respectively to obtain the regression coefficient; If the regression coefficient corresponds to the fault coefficient in the fault diagnosis coefficient, it represents the preliminary regression sub-coefficient of the fault; If the regression coefficient does not correspond to the fault coefficient in the fault diagnosis coefficient, it indicates a preliminary regression sub-coefficient of non-fault; The generation module is used to count all regression sub-coefficients of each device association group and input them into the fault diagnosis tree, extract the normalization coefficients of the regression sub-coefficients of the nodes in the fault diagnosis tree, and generate corresponding analysis results based on all the normalization coefficients.

Images