CN115860588B - Circuit breaker custom health evaluation method based on knowledge graph and extensible model - Google Patents
Circuit breaker custom health evaluation method based on knowledge graph and extensible model Download PDFInfo
- Publication number
- CN115860588B CN115860588B CN202310186835.XA CN202310186835A CN115860588B CN 115860588 B CN115860588 B CN 115860588B CN 202310186835 A CN202310186835 A CN 202310186835A CN 115860588 B CN115860588 B CN 115860588B
- Authority
- CN
- China
- Prior art keywords
- event
- node
- nodes
- sub
- entity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 163
- 238000011156 evaluation Methods 0.000 title claims abstract description 113
- 230000004044 response Effects 0.000 claims abstract description 83
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 40
- 238000004422 calculation algorithm Methods 0.000 claims description 32
- 230000011218 segmentation Effects 0.000 claims description 28
- 238000012986 modification Methods 0.000 claims description 14
- 230000004048 modification Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 230000003993 interaction Effects 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 21
- 230000008569 process Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a circuit breaker custom health evaluation method based on a knowledge graph and a scalable model, which comprises the following steps: a first knowledge graph for carrying out health evaluation on the circuit breaker is constructed in advance; constructing a corresponding second event node for the response event type corresponding to each first event node based on the extensible model; acquiring a circuit breaker and use data of each device included in the circuit breaker, and training the classifier according to all response event types corresponding to the first event node; the trained classifier classifies the use data to obtain a plurality of evaluation sub-indexes, sequentially determines a first entity node, a first event node and a second event node corresponding to the first knowledge graph according to the corresponding evaluation sub-indexes, and calculates based on the second event node to obtain a health sub-coefficient; and counting the health sub-coefficients output by all the second event nodes to obtain the total health evaluation coefficient of the corresponding breaker, and outputting a health evaluation result according to the total health evaluation coefficient.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a circuit breaker custom health evaluation method based on a knowledge graph and an extensible model.
Background
In the generation, transportation and use of electricity, power distribution is an extremely important link. The distribution system comprises a transformer and various high-low voltage electrical equipment, and a circuit breaker is an electrical appliance with wide application range.
In the actual use process, whether the circuit breaker is healthy or not is related to the stability of the whole power supply line, and because certain differences exist in the types and the structures of the circuit breakers used in different lines, the circuit breaker cannot be subjected to customized health evaluation aiming at the differences of the circuit breaker structures in the prior art, and certain office limitations exist in the health evaluation of the circuit breaker.
Disclosure of Invention
The embodiment of the invention provides a self-defined health evaluation method for a circuit breaker based on a knowledge graph and an extensible model, which can perform self-defined health evaluation on the circuit breaker based on the knowledge graph and the extensible model, so that the method is suitable for effectively evaluating the health of circuit breakers of different models, structures and application scenes.
In a first aspect of the embodiment of the present invention, a method for evaluating self-defined health of a circuit breaker based on a knowledge graph and a scalable model is provided, including:
a first knowledge graph for carrying out health evaluation on the circuit breaker is constructed in advance, wherein the first knowledge graph comprises a plurality of groups of corresponding first entity nodes and first event nodes, the first entity nodes are various entity devices included in the circuit breaker, and the first event nodes are response events corresponding to the corresponding entity devices;
constructing a corresponding second event node for the response event type corresponding to each first event node based on the extensible model, wherein the second event node comprises second event information for calculating a health sub-coefficient according to the response event type;
when judging that the circuit breaker needs to be subjected to health evaluation, acquiring the circuit breaker and the use data of each device included in the circuit breaker, and training the classifier according to all response event types corresponding to the first event node, so that all response event types corresponding to the first event node serve as classification targets of the classifier;
the trained classifier classifies the use data to obtain a plurality of evaluation sub-indexes, sequentially determines a first entity node, a first event node and a second event node corresponding to the first knowledge graph according to the corresponding evaluation sub-indexes, and calculates based on the second event node to obtain a health sub-coefficient;
And counting the health sub-coefficients output by all the second event nodes to obtain the total health evaluation coefficient of the corresponding breaker, and outputting a health evaluation result according to the total health evaluation coefficient.
Optionally, in one possible implementation manner of the first aspect, the pre-constructing a first knowledge graph for performing health evaluation on the circuit breaker, where the first knowledge graph includes multiple groups of corresponding first entity nodes and first event nodes, the first entity nodes are various entity devices included in the circuit breaker, and the first event nodes are response events corresponding to the corresponding entity devices, and includes:
receiving map configuration data input by a user, wherein the map configuration data at least comprises first entity nodes and/or first event nodes, each first entity node has a corresponding entity node label, and each first event node has a corresponding event node label;
a second entity node corresponding to the circuit breaker is pre-constructed, and the first entity node is connected with the second entity node and/or other first entity nodes according to entity node labels of all the first entity nodes, wherein the entity node labels have the connection relation of the first entity nodes;
And connecting the first event node with the second entity node and/or the first entity node according to event node labels of all the first event nodes, wherein the event node labels have connection relations of the first event node.
Optionally, in one possible implementation manner of the first aspect, the method further includes:
traversing all the first entity nodes and determining a first event node connected with each first entity node;
if the first entity node which is not connected with the first event node exists, the corresponding first entity node is used as a third entity node, and the third entity node is displayed in a knowledge graph according to a preset form;
if the third event node corresponding to the user configuration and the third entity node is judged to be received, the third entity node is connected with the third event node;
if the third event node corresponding to the user configuration and the third entity node is not received or an instruction for hiding the third entity node by the user is received, hiding the third entity node.
Optionally, in a possible implementation manner of the first aspect, the constructing, based on the extensible model, a corresponding second event node for a response event type corresponding to each first event node, where the second event node includes second event information that calculates a health sub-coefficient according to the response event type includes:
Counting response event types corresponding to all first event nodes by using the extensible model, generating a third event node initially corresponding to each first event node according to the response event types, wherein the first event nodes are arranged in one-to-one correspondence with the third event nodes;
the extensible model displays the connection relation between all the first event nodes and the third event nodes;
if the confirmation information of the user is received, taking all the third event nodes as second event nodes;
the extensible model counts all the second event nodes to generate a node configuration list, and the second event information of each second event node is determined by interaction with a user according to the node configuration list.
Optionally, in one possible implementation manner of the first aspect, the method further includes:
if the merging information of the user is received, determining a third event node needing merging modification and a third event node not needing merging modification according to the merging information;
combining a plurality of third event nodes needing to be combined and modified according to the combination information to obtain a first type of second event node, wherein the first type of second event node is connected with a plurality of first event nodes;
Taking a third event node which does not need to be combined and modified as a second event node of a second type, wherein the second event node of the second type is connected with one first event node;
the extensible model counts all the second event nodes to generate a node configuration list, and the second event information of each second event node is determined by interaction with a user according to the node configuration list.
Optionally, in a possible implementation manner of the first aspect, the generating, by the extensible model, a node configuration list by counting all second event nodes, and determining second event information of each second event node according to interaction between the node configuration list and a user includes:
the extensible model counts the response event types corresponding to all the second event nodes to generate a node configuration list, wherein the node configuration list comprises a plurality of node configuration units corresponding to the second time nodes one by one, and each node configuration unit comprises a node type column and an event information configuration column corresponding to each node type column;
receiving second event information configured by a user for each event information configuration column based on the node configuration list;
after judging that the user inputs the configuration completion information of the node configuration list, if all event information configuration columns and the second event nodes of the node configuration unit respectively have corresponding second event information, the user completes the configuration of the second event information of each second event node;
The extensible model determines second event nodes corresponding to event information configuration columns without second event information and node configuration units, takes the corresponding second event nodes as fourth event nodes, counts all the fourth event nodes in the first knowledge graph, and performs hiding processing on the first event nodes and the first entity nodes connected with the fourth event nodes.
Optionally, in a possible implementation manner of the first aspect, the receiving, based on the node configuration list, second event information configured by a user for each event information configuration column includes:
the expandable model root compares the response event types corresponding to each event information configuration column with an algorithm library, and if the comparison results correspond, corresponding healthy initial sub-algorithms are determined, wherein each healthy initial sub-algorithm has a corresponding initial sub-life value;
the expandable model modifies the initial sub-life value based on the life modification information corresponding to each response event type to obtain second event information modified and configured by the user;
if the comparison result does not correspond to the result, the health configuration sub-algorithm configured by the user in the event information configuration column is received, and the health configuration sub-algorithm is used as second event information configured by the user.
Optionally, in one possible implementation manner of the first aspect, the classifying, by the trained classifier, the usage data to obtain a plurality of evaluation sub-indexes, sequentially determining, according to the corresponding evaluation sub-indexes, a first entity node, a first event node, and a second event node corresponding to the first knowledge graph, and calculating based on the second event node to obtain a health sub-coefficient, where the calculating includes:
performing word segmentation processing on the evaluation sub-index to obtain equipment name word segmentation, equipment response event word segmentation and equipment response frequency word segmentation;
determining corresponding first entity nodes according to the equipment name word segmentation corresponding to the evaluation sub-index, determining first event nodes connected with the first entity nodes according to the equipment response event word segmentation, and determining connected second event nodes according to the determined first event nodes;
if the corresponding second event node is judged to be the first type second event node, calculating based on a health configuration sub-algorithm corresponding to the second event node after receiving all equipment response times word segmentation to obtain a first type health sub-coefficient;
if the corresponding second event node is judged to be the second event node of the second type, calculating based on a health configuration sub-algorithm corresponding to the second event node after receiving the equipment response frequency word segmentation to obtain a health sub-coefficient of the second type.
Optionally, in one possible implementation manner of the first aspect, the method further includes:
the first type of healthy sub-coefficients and the second type of healthy sub-coefficients are calculated by the following formulas,
wherein ,
for the first type of healthy sub-coefficients,
to calculate the first type of health sub-coefficient
The device response times of the second event nodes are segmented,
to calculate the first type of health sub-coefficient
The initial sub-lifetime value of the second event node,
to calculate the first type of health sub-coefficient
The calculated gradient values of the second event nodes,
to calculate the upper limit of the number of first event nodes corresponding to the second event nodes when the first type of health sub-coefficients,
to calculate the number of first event nodes corresponding to the second event nodes when the first type of health sub-coefficients,
for the second type of healthy sub-coefficients,
to calculate the device response times for the second type of healthy sub-coefficients,
to calculate an initial sub-life value for the second type of healthy sub-coefficients.
Optionally, in one possible implementation manner of the first aspect, the counting the health sub-coefficients output by all the second event nodes to obtain a health evaluation total coefficient of the corresponding circuit breaker, and outputting a health evaluation result according to the health evaluation total coefficient includes:
Counting the health sub-coefficients output by all the second event nodes, and determining the event node weight corresponding to each second event node;
comprehensively calculating according to the health sub-coefficient and the event node weight corresponding to each second event node to obtain the health evaluation total coefficient of the corresponding breaker, obtaining the health evaluation total coefficient through the following formula,
wherein ,
for the overall coefficient of health assessment,
is the first
Health sub-coefficients corresponding to the second event nodes,
is the first
Sub-weights corresponding to the second event nodes,
as an upper limit value for the number of second event nodes,
a number value for the second event node;
comparing the total health evaluation coefficient with a preset coefficient interval, and determining the preset coefficient interval in which the total health evaluation coefficient is located to obtain a corresponding health evaluation result, wherein each preset coefficient interval has a corresponding health evaluation result.
Optionally, in one possible implementation manner of the first aspect, counting the number of all the hidden third entity nodes in the first knowledge graph to obtain a hidden entity node counted number, counting the number of all the first entity nodes in the first knowledge graph to obtain a display entity node counted number, and calculating according to the hidden entity node counted number and the display entity node counted number to obtain a hidden entity node duty ratio coefficient;
Counting all fourth event nodes in the first knowledge graph, and the number of hidden branches formed by the first event nodes connected with the fourth event nodes and the first entity nodes, counting the number of second event nodes in the first knowledge graph to obtain the number of display branches, and obtaining a display weight value of the corresponding number of display branches according to the number of first event nodes corresponding to each second event node;
calculating according to the number of the hidden branches, the number of the display branches and the display weight value to obtain a hidden branch duty ratio coefficient;
calculating according to the hidden entity node duty ratio coefficient and the hidden branch duty ratio coefficient to obtain an integrity evaluation coefficient of the first knowledge graph, and generating credibility corresponding to the health evaluation result according to the integrity evaluation coefficient.
In a second aspect of the embodiments of the present invention, there is provided a storage medium having stored therein a computer program for implementing the method of the first aspect and the various possible designs of the first aspect when the computer program is executed by a processor.
According to the circuit breaker self-defined health evaluation method based on the knowledge graph and the extensible model, the first knowledge graph can be constructed based on interaction between the extensible model and a user, and the health sub-coefficients corresponding to each entity device included in the circuit breaker are calculated one by one according to the corresponding relation among the first entity node, the first event node and the second event node, and the corresponding health sub-coefficients are fused to obtain a final health evaluation result of the corresponding circuit breaker. The invention can construct the first knowledge maps corresponding to different circuit breakers according to different types and structures of the circuit breakers based on the expandable model, so that the invention can construct different first knowledge maps aiming at different circuit breakers, and can be applied to health evaluation scenes of various types of circuit breakers.
According to the technical scheme provided by the invention, the connection relation of the entity node and the event node is automatically verified in the construction process of the entity node and the event node, and when the corresponding entity node and the event node cannot form a sub-branch for calculating the health sub-coefficient, the corresponding entity node and the event node are subjected to hiding treatment, so that all the entity node and the event node in the method participate in calculation. In addition, when the second event information of the second event nodes is obtained, the method and the device can count all the second event nodes to generate the node configuration list, acquire the second event information based on the node configuration list, and improve the acquisition efficiency of the second event information.
According to the method and the device, in the construction process of the first knowledge graph, branches formed by a plurality of first event nodes can be combined according to calculation requirements, so that the first knowledge graph is more diversified, and different calculation scenes can be met.
According to the invention, the integrity of the first knowledge graph can be correspondingly evaluated through the integrity evaluation coefficient, so that guidance of staff on the integral construction of the first knowledge graph is realized, the node dimension in the first knowledge graph is more, and the health evaluation of the circuit breaker is more accurate. According to the method, the credibility of the corresponding knowledge graph is obtained through calculation according to the complete condition of the first knowledge graph, and the corresponding health evaluation result is effectively evaluated by combining the credibility of the corresponding knowledge graph.
Drawings
FIG. 1 is a flow chart of a method for circuit breaker custom health evaluation based on knowledge graph and extensible model;
fig. 2 is a schematic structural diagram of the first knowledge graph.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein.
It should be understood that, in various embodiments of the present invention, the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present invention, "plurality" means two or more. "and/or" is merely an association relationship describing an association object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "comprising A, B and C", "comprising A, B, C" means that all three of A, B, C comprise, "comprising A, B or C" means that one of the three comprises A, B, C, and "comprising A, B and/or C" means that any 1 or any 2 or 3 of the three comprises A, B, C.
It should be understood that in the present invention, "B corresponding to a", "a corresponding to B", or "B corresponding to a" means that B is associated with a, from which B can be determined. Determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information. The matching of A and B is that the similarity of A and B is larger than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection" depending on the context.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
The invention provides a circuit breaker custom health evaluation method based on a knowledge graph and a scalable model, which is shown in fig. 1 and comprises the following steps:
step S110, a first knowledge graph for health evaluation of the circuit breaker is pre-constructed, wherein the first knowledge graph comprises a plurality of groups of corresponding first entity nodes and first event nodes, the first entity nodes are various entity devices included in the circuit breaker, and the first event nodes are response events corresponding to the corresponding entity devices. The invention can pre-construct a first knowledge graph for carrying out health evaluation on the circuit breaker, and carry out health evaluation on the circuit breaker through entity nodes and event nodes included in the knowledge graph. The first entity nodes in the first knowledge graph are all entity devices and equipment related to the circuit breaker, and the first entity nodes can correspond to the circuit breaker and also can correspond to part equipment such as a tripper and an arc extinguishing chamber included in the circuit breaker. The first event node corresponds to a response event corresponding to the corresponding physical structure, for example, the first entity node is an under-voltage release, and when an under-voltage condition occurs at the circuit breaker, the under-voltage release is caused to respond to a response event for controlling the circuit breaker to open, and the event can be regarded as event content included in the first event node.
In one possible implementation manner, the step S110 includes:
and receiving map configuration data input by a user, wherein the map configuration data at least comprises first entity nodes and/or first event nodes, each first entity node has a corresponding entity node label, and each first event node has a corresponding event node label. When initializing the first knowledge graph, the user can actively configure the graph, and the invention receives the graph configuration data input by the user, wherein the graph configuration data can comprise corresponding first entity nodes and/or first event nodes. The entity node labels have connection relations of the first entity node, and the event node labels have connection relations of the event node.
And constructing a second entity node corresponding to the circuit breaker in advance, and connecting the first entity node with the second entity node and/or other first entity nodes according to entity node labels of all the first entity nodes, wherein the entity node labels have the connection relation of the first entity nodes. The invention constructs a second entity node corresponding to the breaker, wherein the second entity node can be regarded as an initial node. At this time, there are some first entity nodes connected with the second entity nodes, and some first entity nodes connected with other first entity nodes.
And connecting the first event node with the second entity node and/or the first entity node according to event node labels of all the first event nodes, wherein the event node labels have connection relations of the first event node. The present invention connects different first event nodes with corresponding first entity nodes according to event node labels of all the first event nodes, and typically, each first entity node has a corresponding first event node.
In one possible implementation manner, the technical scheme provided by the invention further comprises:
all the first entity nodes are traversed and the first event node to which each first entity node is connected is determined. After the first entity nodes and the first event nodes are connected, the first entity nodes are traversed, and the first event node corresponding to each first entity node is determined.
If the first entity node which is not connected with the first event node exists, the corresponding first entity node is used as a third entity node, and the third entity node is displayed in the knowledge graph according to a preset form. At this time, the corresponding first entity node does not have a corresponding first event node, and at this time, the user does not configure a corresponding response event for the device corresponding to the first entity node, so at this time, the present invention takes the corresponding first entity node as a third entity node, and displays the third entity node in a preset form, so as to achieve the purpose of reminding the user. The preset shape may be to increase its volume, to fix the color for display, etc.
And if the third event node corresponding to the user configuration and the third entity node is received, connecting the third entity node with the third event node. At this time, after receiving the reminder, the user configures a corresponding third event node for a corresponding third entity node, the third entity node is converted into the first entity node again, the third event node is also converted into the first event node again, and the third entity node is not displayed according to a preset state.
If the third event node corresponding to the user configuration and the third entity node is not received or an instruction for hiding the third entity node by the user is received, hiding the third entity node. At this time, the user does not configure the third event node for the third entity node, and the health evaluation dimension corresponding to the corresponding third entity node cannot perform support calculation, so that the corresponding third entity node needs to be hidden at this time. When the instruction for hiding the third entity node is directly received, the method and the device can actively hide the third entity node. The hiding process is to avoid active display of the corresponding entity node.
Step S120, constructing a corresponding second event node for the response event type corresponding to each first event node based on the extensible model, wherein the second event node comprises second event information for calculating a health sub-coefficient according to the response event type. The invention can combine the expandable model to construct corresponding second event nodes for all response event types, and different second event nodes can have different response event types to calculate health sub-coefficients. For example, the first event node is "when an under-voltage condition occurs at the circuit breaker, the under-voltage release is caused to respond to a response event for controlling the circuit breaker to open", and the second event information at this time may be "the circuit breaker is opened according to the under-voltage release includes the health calculation performed, and the obtained health sub-coefficient" may include a calculation formula.
In one possible implementation manner, the step S120 includes:
the expandable model counts the types of response events corresponding to all the first event nodes, and generates a third event node corresponding to each first event node initially according to the types of response events, wherein the first event nodes and the third event nodes are arranged in a one-to-one correspondence. The extensible model in the invention can count the types of response events corresponding to all the first event nodes, and generates a corresponding third event node for each first event node, wherein the content of the third event node can be empty.
And the extensible model displays the connection relation between all the first event nodes and the third event nodes. The invention will be presented with respect to the first event node and the third event node, where the first event node and the third event node are in one-to-one correspondence.
And if the confirmation information of the user is received, taking all the third event nodes as the second event nodes. In this case, the response time corresponding to each first event node is calculated separately, and the corresponding third event node is used as the second event node. At this time, each first event node and each second event node are set in a one-to-one correspondence.
The extensible model counts all the second event nodes to generate a node configuration list, and the second event information of each second event node is determined by interaction with a user according to the node configuration list. The extensible model generates node configuration lists for all the second event nodes, and interacts with the node configuration lists to enable a user to determine second event information of each second event node, namely determining a calculation mode of a corresponding response event according to the node configuration lists.
In one possible implementation manner, the technical scheme provided by the invention further comprises:
And if the merging information of the user is received, determining a third event node needing merging modification and a third event node not needing merging modification according to the merging information. At this time, the user needs to combine the plurality of third event nodes, so that the third event nodes requiring combining modification and the third event nodes not requiring combining modification can be respectively determined by combining the combining information at this time.
And combining the plurality of third event nodes needing to be combined and modified according to the combination information to obtain a first type of second event node, wherein the first type of second event node is connected with the plurality of first event nodes. The invention can combine the third event nodes to be combined according to the combination information to obtain the first type of second event nodes, and one second event node at the moment can correspond to a plurality of first event nodes, namely when the second event node is used for calculating a certain health dimension, the response events of the plurality of first event nodes are required to be calculated.
And taking the third event node without merging modification as a second event node of a second type, wherein the second event node of the second type is connected with one first event node. At this time, the corresponding second event node and the first event node are in one-to-one correspondence.
The extensible model counts all the second event nodes to generate a node configuration list, and the second event information of each second event node is determined by interaction with a user according to the node configuration list. As described above, the extensible model generates node configuration lists for all the second event nodes, and interacts with the node configuration lists to enable the user to determine the second event information of each second event node, i.e. determine the calculation mode of the corresponding response event according to the node configuration lists.
In one possible implementation manner, the method for generating the node configuration list by counting all the second event nodes by the extensible model includes the steps of:
the extensible model counts the response event types corresponding to all the second event nodes to generate a node configuration list, the node configuration list comprises a plurality of node configuration units corresponding to the second time nodes one by one, and each node configuration unit comprises a node type column and an event information configuration column corresponding to each other one by one. The extensible model in the invention can count all response event types and generate a node configuration list, wherein a node type column is used for filling the response event types, and an event information configuration column is used for filling corresponding second event information.
And receiving second event information configured by the user for each event information configuration column based on the node configuration list. The invention displays the node configuration list, interacts with the user according to the node configuration list, and receives the second event information configured by the user for each event information configuration column.
After judging that the user inputs the configuration completion information of the node configuration list, if all event information configuration columns and the second event nodes of the node configuration unit respectively have corresponding second event information, the user completes the configuration of the second event information of each second event node. After the user completes the configuration of the node configuration list, the user is proved to have configured the required calculation algorithm, and the possible situation that all event information configuration columns and second event nodes have corresponding second event information at the moment can be regarded as that the user configures all the second event information at the moment.
The extensible model determines second event nodes corresponding to event information configuration columns without second event information and node configuration units, takes the corresponding second event nodes as fourth event nodes, counts all the fourth event nodes in the first knowledge graph, and performs hiding processing on the first event nodes and the first entity nodes connected with the fourth event nodes. In some situations, an event information configuration column configured with the second event information may appear, in which the user does not actively configure the event information for various reasons, so that the present invention takes the second event node configured with the second event information as a fourth event node, and performs hiding processing on all the fourth event node, and the first event node and the first entity node connected with the fourth event node, where the manner can ensure that all branches formed by the second event node that are not subjected to hiding processing participate in calculation.
In one possible implementation manner, the method for receiving the second event information configured by the user for each event information configuration column based on the node configuration list includes:
and the expandable model root compares the response event types corresponding to each event information configuration column with the algorithm library, and if the comparison result is corresponding, the corresponding healthy initial sub-algorithm is determined, and each healthy initial sub-algorithm has a corresponding initial sub-life value. The invention can compare the response event types corresponding to each event information configuration column, and determine the healthy initial sub-algorithm corresponding to the algorithm library, wherein each healthy initial sub-algorithm has a corresponding initial sub-life value. For example, the circuit breaker includes an under-voltage release, and the effective usage number of the under-voltage release is 1000, and then the initial sub-life value at this time is 1000. For example, the healthy initial sub-algorithm is a (1-usage number/initial sub-lifetime) value, and the usage number is 100 times at this time, and the calculation mode of the healthy initial sub-algorithm at this time is (1-100/1000).
The expandable model modifies the initial sub-life value based on the life modification information corresponding to each response event type, and second event information of modification configuration is obtained for the user. In an actual application scenario, because the types of the circuit breakers may be different, the specifications and materials of the tripper and the arc extinguishing chamber may be different, so that certain differences in corresponding service lives may be caused, and therefore, the initial sub-life values of the entities corresponding to each first entity node may need to be modified.
If the comparison result does not correspond to the result, the health configuration sub-algorithm configured by the user in the event information configuration column is received, and the health configuration sub-algorithm is used as second event information configured by the user. At this time, the algorithm library does not have sub-algorithms corresponding to the corresponding entities, so that the user is required to perform active configuration, and at this time, the effective configuration of the sub-algorithms for health configuration by the user is received through the event information configuration column.
Through the steps, the interactive configuration of the first knowledge graph is realized, and the first knowledge graph after the interactive configuration can be shown in fig. 2.
And step 130, when judging that the health evaluation needs to be carried out on the circuit breaker, acquiring the circuit breaker and the use data of each device included in the circuit breaker, and training the classifier according to all response event types corresponding to the first event node, so that all response event types corresponding to the first event node serve as classification targets of the classifier. When the health evaluation is carried out on the circuit breaker, the invention actively acquires the circuit breaker and the use data of each device included in the circuit breaker, trains the classifier according to the response event types, classifies all the use data through the classifier, and obtains corresponding classification targets. The classification targets at this time may be the response times of the under-voltage release, the operation times of the arc extinguishing chamber, the response times of the overvoltage, and the like. In the training process of the classifier, the classifier is trained according to all response event types corresponding to the first event node, so that the classifier is classified into information and data which need to be calculated.
Step S140, the trained classifier classifies the use data to obtain a plurality of evaluation sub-indexes, sequentially determines a first entity node, a first event node and a second event node corresponding to the first knowledge graph according to the corresponding evaluation sub-indexes, and calculates based on the second event node to obtain a health sub-coefficient. After the trained classifier classifies the use data, a plurality of evaluation sub-indexes are obtained, wherein the evaluation sub-indexes are the response times of the undervoltage release, the working times of the arc extinguishing chamber and the like.
In one possible implementation manner, the step S140 includes:
and performing word segmentation processing on the evaluation sub-index to obtain equipment name word segmentation, equipment response event word segmentation and equipment response frequency word segmentation. The invention performs word segmentation processing on the evaluation sub-index, and at least a plurality of corresponding word segments are obtained.
And determining corresponding first entity nodes according to the equipment name word segmentation corresponding to the evaluation sub-index, determining first event nodes connected with the first entity nodes according to the equipment response event word segmentation, and determining connected second event nodes according to the determined first event nodes. The invention can determine different nodes according to different segmentation words, namely sequentially determining the first entity node, the first event node and the second event node according to a plurality of segmentation words, wherein a calculation chain is formed among each group of the first entity node, the first event node and the second event node.
If the corresponding second event node is judged to be the first type second event node, calculating based on a health configuration sub-algorithm corresponding to the second event node after receiving all equipment response times word segmentation to obtain a first type health sub-coefficient. When the second event node is the first type second event node, a plurality of equipment dimensions are needed to be synthesized for calculation at the moment, and the corresponding first type health sub-coefficient is obtained. For example, when the thermal trip and the magnetic trip need to be combined and calculated in calculating the health sub-coefficients, the calculation is performed based on the health configuration sub-algorithm corresponding to the second event node after the response times of all the devices of the thermal trip and the magnetic trip are divided, so that the corresponding first type of health sub-coefficients are obtained.
If the corresponding second event node is judged to be the second event node of the second type, calculating based on a health configuration sub-algorithm corresponding to the second event node after receiving the equipment response frequency word segmentation to obtain a health sub-coefficient of the second type. When the second event node is a second event node of a second type, only one equipment dimension is needed to calculate at the moment, and a corresponding health sub-coefficient of the second type is obtained. For example, when the separate excitation release needs to perform separate calculation during calculation of the health sub-coefficient, the calculation is performed based on the health configuration sub-algorithm corresponding to the second event node after the device response frequency word segmentation of the separate excitation release is obtained, so that the corresponding second type of health sub-coefficient is obtained.
In one possible implementation manner, the technical scheme provided by the invention further comprises:
the first type of healthy sub-coefficients and the second type of healthy sub-coefficients are calculated by the following formulas,
wherein ,
for the first type of healthy sub-coefficients,
to calculate the first type health sub-coefficient corresponding to the second event node
The device response times for the first event node are segmented,
to calculate the first type health sub-coefficient corresponding to the second event node
The initial sub-life value of the first event node,
to calculate the first type health sub-coefficient corresponding to the second event node
The calculated gradient values for the first event node,
to calculate the upper limit of the number of first event nodes corresponding to the second event nodes when the first type of health sub-coefficients,
to calculate the number of first event nodes corresponding to the second event nodes when the first type of health sub-coefficients,
for the second type of healthy sub-coefficients,
to calculate the device response times for the second type of healthy sub-coefficients,
to calculate an initial sub-life value for the second type of healthy sub-coefficients.
By passing through
Can calculate the ratio of the corresponding times to the initial sub-life value if 
The larger the
The smaller the corresponding health sub-coefficient, the smaller the calculated gradient value for each first event node may be preset by the operator by
A calculation may be performed to obtain the fused first type of healthy sub-coefficients for all the first event nodes. By passing through
Can calculate the ratio of the corresponding times to the initial sub-life value if
The larger the
The smaller the corresponding healthy sub-coefficient will be.
And step S150, counting the health sub-coefficients output by all the second event nodes to obtain the total health evaluation coefficient of the corresponding circuit breaker, and outputting a health evaluation result according to the total health evaluation coefficient. The invention can count all the health sub-coefficients output by the second event node, namely the expandable model, and can comprehensively calculate all the health sub-coefficients to obtain the total health evaluation coefficient and output the health evaluation result by combining the total health evaluation coefficient.
In one possible implementation manner, the step S150 includes:
and counting the health sub-coefficients output by all the second event nodes, and determining the event node weight corresponding to each second event node. The invention can count the event node weights of different second event nodes, and comprehensively calculate the event node weights by combining the corresponding health sub-coefficients.
Comprehensively calculating according to the health sub-coefficient and the event node weight corresponding to each second event node to obtain the health evaluation total coefficient of the corresponding breaker, obtaining the health evaluation total coefficient through the following formula,
wherein ,
for the overall coefficient of health assessment,
is the first
Health sub-coefficients corresponding to the second event nodes,
is the first
Sub-weights corresponding to the second event nodes,
as an upper limit value for the number of second event nodes,
is the number value of the second event node. By passing through
The sum of the health sub-coefficients weighted by all the second event nodes can be obtained, and the invention is based on
Obtaining the average value of the sum of the health sub-coefficients after weighting if
The larger the corresponding circuit breaker is, the healthier if
The smaller the corresponding circuit breaker may be, the more problematic.
Comparing the total health evaluation coefficient with a preset coefficient interval, and determining the preset coefficient interval in which the total health evaluation coefficient is located to obtain a corresponding health evaluation result, wherein each preset coefficient interval has a corresponding health evaluation result. The preset coefficient interval may be a plurality of preset coefficient intervals, and the invention determines the preset coefficient interval where the total health evaluation coefficient is located and obtains health evaluation results, for example, normal health state, non-health state and the like. The user can judge whether to maintain and replace the corresponding circuit breaker according to the health evaluation result, so that the working stability of the corresponding circuit is ensured.
In one possible implementation manner, the method provided by the invention comprises the steps of counting the number of all hidden third entity nodes in the first knowledge graph to obtain the counted number of hidden entity nodes, and counting the number of all first entity nodes in the first knowledge graph to obtain the counted number of display entity nodes. And calculating according to the statistic quantity of the hidden entity nodes and the statistic quantity of the display entity nodes to obtain the occupancy rate coefficient of the hidden entity nodes. Counting all fourth event nodes in the first knowledge graph and the number of hidden branches formed by the first event nodes connected with the fourth event nodes and the first entity nodes, counting the number of all second event nodes in the first knowledge graph to obtain the number of display branches, obtaining the display weight value of the corresponding number of display branches according to the number of the first event nodes corresponding to each second event node, and calculating according to the number of hidden branches, the number of display branches and the display weight value to obtain the ratio coefficient of the hidden branches. Calculating according to the hidden entity node duty ratio coefficient and the hidden branch duty ratio coefficient to obtain an integrity evaluation coefficient of the first knowledge graph, and generating credibility corresponding to the health evaluation result according to the integrity evaluation coefficient. And if the integrity evaluation coefficient is lower than a preset coefficient, generating reminding information about the first knowledge graph so that a user performs integrity processing on the first knowledge graph and the corresponding first knowledge graph is more complete.
The technical proposal provided by the invention calculates the ratio coefficient of the hidden entity node, the ratio coefficient of the hidden branch, the integrity evaluation coefficient and the credibility through the following formulas,
wherein ,
in order to conceal the physical node duty cycle coefficients,
in order to hide the physical node statistics,
in order to display the entity node statistics,
in order to conceal the bypass duty cycle coefficients,
in order to hide the number of branches,
in order to display the number of branches,
is the first knowledge graph
The display weight values of the individual display branches,
displaying the upper limit value of the branch in the first knowledge graph,
displaying the number value of the branches in the first knowledge graph,
for the integrity-evaluation coefficient,
as the weight value of the node,
as the weight value of the branch circuit,
in order to set the value of the constant value,
in order for the degree of certainty to be a degree of certainty,
is the confidence coefficient.
By passing through
Can calculate the occupancy rate coefficient of the hidden entity node if
The larger the corresponding hidden entity nodes are, the fewer the entity devices the circuit breaker participates in the calculation are, and the smaller the integrity evaluation coefficient and the credibility are. By passing through
To calculate the hidden branch duty cycle coefficient if
The larger, the more corresponding hidden branches, the fewer entity devices and response events involved in calculation of the circuit breaker, the integrity evaluation The smaller the coefficient and the less trustworthiness. The weight value is displayed
May be determined according to the number of corresponding first event nodes in the display branch, and if the number of corresponding first event nodes is larger, the corresponding display weight value is
The larger may be. By node weight value
Can be matched with
Weighting by branch weight value
Can be matched with
Weighting processing is carried out, and node weight value is obtained
Branch weight value
May be preset. At the position of
When the condition of (1) occurs, then
0 or less, the integrity evaluation coefficient at this time may be a preset custom
. The invention can convert the coefficient through the preset credibility
And converting the integrity evaluation coefficient to obtain corresponding credibility.
According to the invention, the integrity of the first knowledge graph can be correspondingly evaluated through the integrity evaluation coefficient, so that guidance of staff on the integral construction of the first knowledge graph is realized, the node dimension in the first knowledge graph is more, and the health evaluation of the circuit breaker is more accurate. According to the method, the credibility of the corresponding knowledge graph is obtained through calculation according to the complete condition of the first knowledge graph, and the corresponding health evaluation result is effectively evaluated by combining the credibility of the corresponding knowledge graph.
The present invention also provides a storage medium having stored therein a computer program for implementing the methods provided by the various embodiments described above when executed by a processor.
The storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). In addition, the ASIC may reside in a user device. The processor and the storage medium may reside as discrete components in a communication device. The storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc.
The present invention also provides a program product comprising execution instructions stored in a storage medium. The at least one processor of the device may read the execution instructions from the storage medium, the execution instructions being executed by the at least one processor to cause the device to implement the methods provided by the various embodiments described above.
In the above embodiments of the terminal or the server, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: applicationSpecific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (6)
1. The circuit breaker self-defined health evaluation method based on the knowledge graph and the extensible model is characterized by comprising the following steps of:
a first knowledge graph for carrying out health evaluation on the circuit breaker is constructed in advance, wherein the first knowledge graph comprises a plurality of groups of corresponding first entity nodes and first event nodes, the first entity nodes are various entity devices included in the circuit breaker, and the first event nodes are response events corresponding to the corresponding entity devices;
constructing a corresponding second event node for the response event type corresponding to each first event node based on the extensible model, wherein the second event node comprises second event information for calculating a health sub-coefficient according to the response event type;
when judging that the circuit breaker needs to be subjected to health evaluation, acquiring the circuit breaker and the use data of each device included in the circuit breaker, and training the classifier according to all response event types corresponding to the first event node, so that all response event types corresponding to the first event node serve as classification targets of the classifier;
the trained classifier classifies the use data to obtain a plurality of evaluation sub-indexes, sequentially determines a first entity node, a first event node and a second event node corresponding to the first knowledge graph according to the corresponding evaluation sub-indexes, and calculates based on the second event node to obtain a health sub-coefficient;
Counting the health sub-coefficients output by all the second event nodes to obtain the total health evaluation coefficient of the corresponding breaker, and outputting a health evaluation result according to the total health evaluation coefficient;
the method includes the steps that a first knowledge graph for carrying out health evaluation on the circuit breaker is pre-constructed, the first knowledge graph comprises a plurality of groups of corresponding first entity nodes and first event nodes, the first entity nodes are various entity devices included in the circuit breaker, the first event nodes are response events corresponding to the corresponding entity devices, and the method comprises the following steps:
receiving map configuration data input by a user, wherein the map configuration data at least comprises first entity nodes and/or first event nodes, each first entity node has a corresponding entity node label, and each first event node has a corresponding event node label;
a second entity node corresponding to the circuit breaker is pre-constructed, and the first entity node is connected with the second entity node and/or other first entity nodes according to entity node labels of all the first entity nodes, wherein the entity node labels have the connection relation of the first entity nodes;
connecting the first event node with the second entity node and/or the first entity node according to event node labels of all the first event nodes, wherein the event node labels have a connection relation of the first event node;
Constructing a corresponding second event node for the response event type corresponding to each first event node based on the extensible model, wherein the second event node comprises second event information for calculating a health sub-coefficient according to the response event type, and the method comprises the following steps:
counting response event types corresponding to all first event nodes by using the extensible model, generating a third event node initially corresponding to each first event node according to the response event types, wherein the first event nodes are arranged in one-to-one correspondence with the third event nodes;
the extensible model displays the connection relation between all the first event nodes and the third event nodes;
if the confirmation information of the user is received, taking all the third event nodes as second event nodes;
counting all second event nodes by the extensible model to generate a node configuration list, and determining second event information of each second event node according to interaction between the node configuration list and a user;
the trained classifier classifies the usage data to obtain a plurality of evaluation sub-indexes, sequentially determines a first entity node, a first event node and a second event node corresponding to the first knowledge graph according to the corresponding evaluation sub-indexes, calculates based on the second event node to obtain a health sub-coefficient, and comprises the following steps:
Performing word segmentation processing on the evaluation sub-index to obtain equipment name word segmentation, equipment response event word segmentation and equipment response frequency word segmentation;
determining corresponding first entity nodes according to the equipment name word segmentation corresponding to the evaluation sub-index, determining first event nodes connected with the first entity nodes according to the equipment response event word segmentation, and determining connected second event nodes according to the determined first event nodes;
if the corresponding second event node is judged to be the first type second event node, calculating based on a health configuration sub-algorithm corresponding to the second event node after receiving all equipment response times word segmentation to obtain a first type health sub-coefficient;
if the corresponding second event node is judged to be the second event node of the second type, calculating based on a health configuration sub-algorithm corresponding to the second event node after receiving a device response time word segmentation to obtain a health sub-coefficient of the second type;
the statistics is carried out on the health sub-coefficients output by all the second event nodes to obtain the total health evaluation coefficient of the corresponding breaker, and the health evaluation result is output according to the total health evaluation coefficient, and the method comprises the following steps:
Counting the health sub-coefficients output by all the second event nodes, and determining the event node weight corresponding to each second event node;
comprehensively calculating according to the health sub-coefficient and the event node weight corresponding to each second event node to obtain the health evaluation total coefficient of the corresponding breaker, obtaining the health evaluation total coefficient through the following formula,
wherein ,
for health evaluation total coefficient, ++>
Is->
Health sub-coefficients corresponding to the second event node, < ->
Is->
Sub-weights corresponding to the second event nodes, < ->
For the upper limit value of the number of second event nodes, < >>
A number value for the second event node;
comparing the total health evaluation coefficient with a preset coefficient interval, and determining the preset coefficient interval in which the total health evaluation coefficient is located to obtain a corresponding health evaluation result, wherein each preset coefficient interval has a corresponding health evaluation result.
2. The knowledge graph and extensible model-based circuit breaker custom health evaluation method of claim 1, further comprising:
traversing all the first entity nodes and determining a first event node connected with each first entity node;
if the first entity node which is not connected with the first event node exists, the corresponding first entity node is used as a third entity node, and the third entity node is displayed in a knowledge graph according to a preset form;
If the third event node corresponding to the user configuration and the third entity node is judged to be received, the third entity node is connected with the third event node;
if the third event node corresponding to the user configuration and the third entity node is not received or an instruction for hiding the third entity node by the user is received, hiding the third entity node.
3. The knowledge graph and extensible model-based circuit breaker custom health evaluation method of claim 1, further comprising:
if the merging information of the user is received, determining a third event node needing merging modification and a third event node not needing merging modification according to the merging information;
combining a plurality of third event nodes needing to be combined and modified according to the combination information to obtain a first type of second event node, wherein the first type of second event node is connected with a plurality of first event nodes;
taking a third event node which does not need to be combined and modified as a second event node of a second type, wherein the second event node of the second type is connected with one first event node;
the extensible model counts all the second event nodes to generate a node configuration list, and the second event information of each second event node is determined by interaction with a user according to the node configuration list.
4. The method for evaluating the custom health of the circuit breaker based on the knowledge graph and the extensible model according to any one of claims 1 or 3, wherein,
the extensible model counts all second event nodes to generate a node configuration list, and determines second event information of each second event node by interaction with a user according to the node configuration list, and the method comprises the following steps:
the extensible model counts the response event types corresponding to all the second event nodes to generate a node configuration list, wherein the node configuration list comprises a plurality of node configuration units corresponding to the second time nodes one by one, and each node configuration unit comprises a node type column and an event information configuration column corresponding to each node type column;
receiving second event information configured by a user for each event information configuration column based on the node configuration list;
after judging that the user inputs the configuration completion information of the node configuration list, if all event information configuration columns and the second event nodes of the node configuration unit respectively have corresponding second event information, the user completes the configuration of the second event information of each second event node;
the extensible model determines second event nodes corresponding to event information configuration columns without second event information and node configuration units, takes the corresponding second event nodes as fourth event nodes, counts all the fourth event nodes in the first knowledge graph, and performs hiding processing on the first event nodes and the first entity nodes connected with the fourth event nodes.
5. The method for evaluating the custom health of the circuit breaker based on the knowledge graph and the extensible model of claim 4, wherein the method comprises the steps of,
the receiving, based on the node configuration list, second event information configured by a user for each event information configuration column includes:
the expandable model root compares the response event types corresponding to each event information configuration column with an algorithm library, and if the comparison results correspond, corresponding healthy initial sub-algorithms are determined, wherein each healthy initial sub-algorithm has a corresponding initial sub-life value;
the expandable model modifies the initial sub-life value based on the life modification information corresponding to each response event type to obtain second event information modified and configured by the user;
if the comparison result does not correspond to the result, the health configuration sub-algorithm configured by the user in the event information configuration column is received, and the health configuration sub-algorithm is used as second event information configured by the user.
6. The knowledge graph and extensible model-based circuit breaker custom health evaluation method of claim 1, further comprising:
the first type of healthy sub-coefficients and the second type of healthy sub-coefficients are calculated by the following formulas,
wherein ,
for the first type of healthy sub-coefficients, +.>
For calculating the healthy sub-coefficients of the first type +.>
The device response times of the second event node are divided into words,>
for calculating the healthy sub-coefficients of the first type +.>
An initial sub-lifetime value of the second event node, a>
For calculating the healthy sub-coefficients of the first type +.>
Calculated gradient values of the second event node, < >>
For calculating the upper limit value of the number of the first event nodes corresponding to the second event nodes when the first type of health sub-coefficients is calculated, +.>
For calculating the number value of the first event node corresponding to the second event node when the first type of health sub-coefficients,/for the first event node>
For the second type of healthy sub-coefficient, +.>
For the device response times in calculating the second type of healthy sub-coefficients, word +.>
To calculate an initial sub-life value for the second type of healthy sub-coefficients.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310186835.XA CN115860588B (en) | 2023-03-02 | 2023-03-02 | Circuit breaker custom health evaluation method based on knowledge graph and extensible model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310186835.XA CN115860588B (en) | 2023-03-02 | 2023-03-02 | Circuit breaker custom health evaluation method based on knowledge graph and extensible model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115860588A CN115860588A (en) | 2023-03-28 |
| CN115860588B true CN115860588B (en) | 2023-06-16 |
Family
ID=85659588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310186835.XA Active CN115860588B (en) | 2023-03-02 | 2023-03-02 | Circuit breaker custom health evaluation method based on knowledge graph and extensible model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115860588B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112632225B (en) * | 2020-12-29 | 2022-08-30 | 天津汇智星源信息技术有限公司 | Semantic searching method and device based on case and event knowledge graph and electronic equipment |
| CN112990656B (en) * | 2021-02-05 | 2023-05-05 | 南方电网调峰调频发电有限公司信息通信分公司 | Health evaluation system and health evaluation method for IT equipment monitoring data |
| US20220309388A1 (en) * | 2021-03-29 | 2022-09-29 | Allstate Insurance Company | Systems and Methods for Classification and Time Series Calibration in Identity Health Analysis |
| CN114357197B (en) * | 2022-03-08 | 2022-07-26 | 支付宝(杭州)信息技术有限公司 | Event reasoning method and device |
| CN114722974B (en) * | 2022-06-07 | 2022-09-02 | 国网浙江省电力有限公司信息通信分公司 | Multi-dimensional map fusion method based on matter logic and entity knowledge |
| CN114817575B (en) * | 2022-06-24 | 2022-09-02 | 国网浙江省电力有限公司信息通信分公司 | Large-scale electric power affair map processing method based on extended model |
-
2023
- 2023-03-02 CN CN202310186835.XA patent/CN115860588B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115860588A (en) | 2023-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Efficient calibration techniques for large-scale traffic simulators | |
| Heiss | Structural choice analysis with nested logit models | |
| RU2598601C2 (en) | Data processing device, data processing method and software | |
| US20130035885A1 (en) | Topology identification in distribution network with limited measurements | |
| US10379146B2 (en) | Detecting non-technical losses in electrical networks based on multi-layered statistical techniques from smart meter data | |
| CN109886328B (en) | Electric vehicle charging facility fault prediction method and system | |
| CN115508770B (en) | KL-NB algorithm-based electric energy meter operation state online evaluation method | |
| CN112750051A (en) | Random forest algorithm-based phase sequence identification method and device for transformer area and terminal equipment | |
| CN114722974B (en) | Multi-dimensional map fusion method based on matter logic and entity knowledge | |
| Ghalmane et al. | Betweenness centrality for networks with non-overlapping community structure | |
| CN108073672A (en) | Business object recommends method, apparatus and electronic equipment | |
| US20220222545A1 (en) | Generation method, non-transitory computer-readable storage medium, and information processing device | |
| CN109213831A (en) | Event detecting method and device calculate equipment and storage medium | |
| CN115860588B (en) | Circuit breaker custom health evaluation method based on knowledge graph and extensible model | |
| Aschidamini et al. | A framework for reliability assessment in expansion planning of power distribution systems | |
| CN113191062B (en) | Power distribution network fault section positioning method and system based on multisource incomplete information | |
| Mercier et al. | Effective resistance against pandemics: Mobility network sparsification for high-fidelity epidemic simulations | |
| Joga et al. | Applications of tunable-Q factor wavelet transform and AdaBoost classier for identification of high impedance faults: Towards the reliability of electrical distribution systems | |
| Carraro et al. | An Eddington ratio-driven origin for the LX− M* relation in quiescent and star-forming active galaxies | |
| CN113298116A (en) | Attention weight-based graph embedding feature extraction method and device and electronic equipment | |
| CN112398226A (en) | Power supply system electricity stealing prevention method, system, terminal and storage medium | |
| CN115018212B (en) | Power generation water consumption prediction analysis method and system and cloud platform | |
| US20220222580A1 (en) | Deterioration detection method, non-transitory computer-readable storage medium, and information processing device | |
| CN113987186B (en) | Method and device for generating marketing scheme based on knowledge graph | |
| Pannala et al. | DINGO: Digital assistant to grid operators for resilience management of power distribution system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |