CN110646710B - Power grid fault intelligent diagnosis method, device, computer equipment and storage medium - Google Patents
Power grid fault intelligent diagnosis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110646710B CN110646710B CN201910952727.2A CN201910952727A CN110646710B CN 110646710 B CN110646710 B CN 110646710B CN 201910952727 A CN201910952727 A CN 201910952727A CN 110646710 B CN110646710 B CN 110646710B
- Authority
- CN
- China
- Prior art keywords
- diagnosed
- fault
- fact
- power grid
- devices
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本申请涉及一种电网故障智能诊断方法、装置、计算机设备和存储介质；所述方法包括接收电网中各待诊断设备上报的遥信报文；读取遥信报文中的故障特征信息，并根据故障特征信息确认事实数据库；调用规则数据库中的预设故障判断规则对事实数据库中的内容进行推理，获取新事实以及对应的解释；在完成推理时，按照获取顺序依次输出新事实以及对应的解释，并根据各新事实以及对应的解释确定诊断结果，实现通过预先基于一阶谓词逻辑形成的各待诊断设备之间关系的规则表达得到预设故障判断规则，对遥信报文中的故障特征信息进行逻辑推理，获取新事实和对应的解释，并依据新事实和对应的解释获取诊断结果，从而提高了故障诊断的准确性。
The present application relates to a power grid fault intelligent diagnosis method, device, computer equipment and storage medium; the method includes receiving remote signaling messages reported by devices to be diagnosed in the power grid; reading fault feature information in the remote signaling messages, and Confirm the fact database according to the fault feature information; invoke the preset fault judgment rules in the rule database to infer the content in the fact database, and obtain new facts and corresponding explanations; when the inference is completed, the new facts and corresponding explanations are output in the order of acquisition. Explain, and determine the diagnosis result according to each new fact and the corresponding explanation, realize the pre-set fault judgment rule based on the rule expression of the relationship between the devices to be diagnosed formed in advance based on the first-order predicate logic. The feature information is logically reasoned, new facts and corresponding explanations are obtained, and diagnostic results are obtained based on the new facts and corresponding explanations, thereby improving the accuracy of fault diagnosis.
Description
Technical Field
The application relates to the technical field of intelligent reasoning and diagnosis of power grid faults, in particular to a power grid fault intelligent diagnosis method, a power grid fault intelligent diagnosis device, computer equipment and a storage medium.
Background
When the power grid fails, a large amount of remote measuring and remote signaling alarm information is uploaded to a dispatching center. The dispatcher needs to judge the fault type according to the information, and then determines an accident handling scheme. The alarm information caused by serious faults often comes from the association of different voltage levels and monitoring systems thereof, and the message quantity is large, particularly when equipment related to a plurality of stations is in voltage loss or is in switching action. The method realizes the quick screening of the power grid fault alarm information and the automatic fault diagnosis by means of a computer technology and an artificial intelligence technology, can effectively improve the accident processing efficiency, and is also one of key links for realizing the intelligent accident processing of the computer.
For fault diagnosis of the smart power grid, the knowledge-based reasoning method is strict in logic and strong in interpretability, but effective organization of accident handling knowledge is guaranteed by universality and practicability. The expression of related knowledge in the automatic diagnosis of the power grid fault needs to meet two requirements: accurately expressing the logical action relationship between the power grid topological structure and the primary and secondary equipment; secondly, the method for knowledge expression needs to have universality, maintainability and efficiency when being used for fault judgment, but at present, the expression of relevant knowledge in automatic power grid fault diagnosis is insufficient, so the inventor finds that at least the following problems exist in the traditional technology: the traditional power grid fault diagnosis method is poor in universality and difficult to combine accuracy and universality.
Disclosure of Invention
Therefore, it is necessary to provide a power grid fault intelligent diagnosis method, device, computer equipment and storage medium for solving the problems that the conventional power grid fault diagnosis method is poor in universality and has difficulty in combining accuracy and universality.
In order to achieve the above object, an embodiment of the present application provides a power grid fault intelligent diagnosis method, including the following steps:
receiving remote signaling messages reported by each device to be diagnosed in the power grid;
reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed;
calling a preset fault judgment rule in a rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression of the relation between the devices to be diagnosed formed on the basis of first-order predicate logic;
and when the reasoning is finished, sequentially outputting the new facts and the corresponding explanations according to the acquisition sequence, and determining a diagnosis result according to each new fact and the corresponding explanations.
In one embodiment, the method further comprises the following steps:
establishing knowledge expression of object types and attribute relations of the equipment to be diagnosed based on first-order predicate logic;
and expressing action logic among different equipment categories after the fault based on the first-order predicate logic to obtain a preset fault judgment rule.
In one embodiment, the knowledge representation includes a conceptual knowledge representation and a relational knowledge representation;
the concept knowledge expression is a predicate expression of a concept object corresponding to each device to be diagnosed; the relation knowledge expression is the attribute expression of the concept object corresponding to each device to be diagnosed and the relation expression between the attribute expressions.
In one embodiment, the step of establishing knowledge expression between concept objects corresponding to devices to be diagnosed based on first-order predicate logic includes the steps of:
carrying out hierarchical classification on the concept objects corresponding to the equipment to be diagnosed according to the equipment grade and the equipment type;
defining corresponding predicate expressions for the concept objects after hierarchical classification by using an object-oriented method, and generating concept knowledge expressions;
expressing the attribute of the concept object corresponding to each device to be diagnosed and the relation between the attribute and the relation based on the concept knowledge expression, and carrying out one-to-one corresponding constraint on the relation between predicate expressions according to different types of the devices to be diagnosed to generate the relation knowledge expression.
In one embodiment, the step of expressing action logic between different device categories after a fault based on the first-order predicate logic to obtain the preset fault judgment rule includes the steps of:
and performing if-then structural rule expression by taking the concept knowledge expression and the relation knowledge table as a drive based on the logic connection words, the limiting quantifier and the user-defined variables in the first-order predicate logic to obtain a preset fault judgment rule.
In one embodiment, the step of calling the preset fault judgment rule in the rule database to reason the content in the fact database and obtain the new fact and the corresponding explanation includes the steps of:
updating the fact database by using the last new fact;
and calling a preset fault judgment rule to infer the content in the updated fact database, and acquiring a new fact and a corresponding explanation at the next time until no new fact is formed.
In one embodiment, the step of updating the fact database with the last new fact includes the steps of:
if the last new fact is the operation to be executed, the operation to be executed is completed;
and updating the fact database by using the last new fact after the operation to be executed is completed.
An intelligent grid fault diagnosis device, comprising:
the message receiving module is used for receiving remote signaling messages reported by each device to be diagnosed in the power grid;
the fact base forming module is used for reading fault characteristic information in the remote communication message and confirming the fact database according to the fault characteristic information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed;
the reasoning module is used for calling a preset fault judgment rule in the rule database to reason the content in the fact database and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression of the relation between the devices to be diagnosed formed on the basis of first-order predicate logic;
and the conclusion output module is used for sequentially outputting the new facts and the corresponding explanations according to the acquisition sequence when reasoning is finished, and determining a diagnosis result according to each new fact and the corresponding explanations.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
receiving remote signaling messages reported by each device to be diagnosed in the power grid;
reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed;
calling a preset fault judgment rule in a rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression among the devices to be diagnosed formed on the basis of first-order predicate logic;
and when the reasoning is finished, sequentially outputting the new facts and the corresponding interpretations according to the acquisition order, and determining a diagnosis result according to the new facts and the corresponding interpretations.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
receiving remote signaling messages reported by each device to be diagnosed in the power grid;
reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed;
calling a preset fault judgment rule in a rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression among the devices to be diagnosed formed on the basis of first-order predicate logic;
and when the reasoning is finished, sequentially outputting the new facts and the corresponding interpretations according to the acquisition order, and determining a diagnosis result according to the new facts and the corresponding interpretations.
One of the above technical solutions has the following advantages and beneficial effects:
the power grid fault intelligent diagnosis method provided by the embodiments of the application comprises the following steps: receiving remote signaling messages reported by each device to be diagnosed in the power grid; reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; calling a preset fault judgment rule in a rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; when reasoning is finished, new facts and corresponding explanations are sequentially output according to the obtaining sequence, a diagnosis result is determined according to the new facts and the corresponding explanations, a preset fault judgment rule is obtained through rule expression of the relation between the devices to be diagnosed formed in advance based on first-order predicate logic, logic reasoning is carried out on fault characteristic information in a remote communication message, the new facts and the corresponding explanations are obtained, the diagnosis result is obtained according to the new facts and the corresponding explanations, and therefore accuracy of fault diagnosis is improved.
Drawings
FIG. 1 is a schematic flow chart of a power grid fault intelligent diagnosis method in one embodiment;
FIG. 2 is a flowchart illustrating a step of obtaining a predetermined failure determination rule according to an embodiment;
FIG. 3 is an exemplary diagram of predicates in the concept knowledge representation in one embodiment;
FIG. 4 is a schematic flow chart diagram illustrating the step of generating a relational knowledge representation in one embodiment;
FIG. 5 is a schematic flow chart of the inference step in one embodiment;
fig. 6 is a view of a topology of a station a;
FIG. 7 is a schematic flow chart of a power grid fault intelligent diagnosis method in another embodiment;
FIG. 8 is a schematic structural diagram of an intelligent grid fault diagnosis device in one embodiment;
FIG. 9 is a diagram showing an internal configuration of a computer device according to an embodiment.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present application are shown in the drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In a specific application scenario of the power grid fault intelligent diagnosis method of the application:
in the traditional technology, patents and research results related to automatic diagnosis of power grid faults relate to technologies such as an expert system based on production rules, an analytical model, an artificial neural network, a Petri network and a Bayesian network. The expert system method based on the production rule has strong interpretability and clear reasoning process, but the description capability of the rule is limited, so that the expert system method is difficult to deal with fault diagnosis under nonstandard power grid wiring and complex faults. The method based on the analytical model converts fault facts and diagnosis rules into a mathematical model, and the diagnosis problem is converted into an optimization problem to be solved, so that the fault hypothesis most conforming to alarm information is found out, but the complete model is often too high in dimension, the relevant weight in the model is set based on subjectivity, and the efficiency and the accuracy of diagnosis cannot be guaranteed. The method based on the artificial neural network takes the fault alarm information as input and the fault reason as output, trains the diagnosis neural network of the fault area through the fault sample, avoids explicit expression of fault diagnosis knowledge, but has poor interpretability and is difficult to ensure the training effect of large-scale power grids. The Petri network technology is characterized in that a topological relation among equipment, a logical action relation among protection equipment, a breaker and fault equipment are expressed in a directed graph form, a Petri network state is initialized according to fault information, a network state is updated through continuous reasoning, a fault diagnosis result in a stable state is finally obtained, the reasoning speed is high, the universality is poor, a model needs to be reestablished under different power grid structures, the modeling and maintenance workload is large, and the practicability is low.
In order to solve the problems that the conventional power grid fault diagnosis method is poor in universality and difficult to combine accuracy and universality, as shown in the figure, the power grid fault intelligent diagnosis method is provided and comprises the following steps:
step S110, receiving remote signaling messages reported by each device to be diagnosed in the power grid.
It should be noted that, there are devices in the power grid that need to be monitored in real time, and the operation state of the devices is monitored to ensure the operation safety of the power grid. For example, the devices to be diagnosed in the power grid include primary devices, secondary devices, fault devices, and substations, the primary devices may be classified as buses, transformers, lines, breakers, disconnecting links, etc., the secondary devices may be classified as protection devices, automation devices, etc., and the substations may be classified as subscriber stations and non-subscriber stations.
And continuously reporting a remote signaling message to the scheduling center in the running process of the equipment to be diagnosed, wherein the remote signaling message carries equipment information, equipment running information and the like of the equipment to be diagnosed so as to facilitate the scheduling center to monitor the equipment to be diagnosed.
Step S120, reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed.
It should be noted that the scheduling center analyzes the remote signaling message, and identifies the fault feature information corresponding to the device to be diagnosed, in one example, a keyword related to fault diagnosis is configured in advance in the scheduling center, and the fault feature information is identified and read from the remote signaling message based on the keyword. The fault characteristic information comprises a concept object, a state type and operation data, wherein the concept object is a code number set according to the equipment name of the equipment to be diagnosed, can be the equipment name itself, and can also be a naming system different from the equipment name; the state type is the action condition of the equipment to be diagnosed, such as opening, closing, tripping and the like; the operation data is an electrical parameter of the device to be diagnosed, for example, a value of current flowing through the primary device y is 150A (amperes), where 150A is the operation data.
Step S130, calling a preset fault judgment rule in the rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression of the relation between the devices to be diagnosed formed on the basis of first-order predicate logic.
It should be noted that the rule database is used for storing logical inference rules, where the preset fault judgment rule is based on a rule expression of a relationship between devices to be diagnosed in the first-order predicate logical power grid.
The preset failure judgment rule written based on the first-order predicate logic may have various forms, and in one example, a feasible manner is provided, as shown in fig. 2, the preset failure judgment rule is formed based on the following steps:
step S210, establishing knowledge expression between concept objects corresponding to the equipment to be diagnosed based on the first-order predicate logic.
The knowledge expression means defining a conceptual object by using predicates and declaring relationships between the predicates, for example, an affiliation, a category relationship, and the like. The knowledge expression comprises a concept knowledge expression and a relation knowledge expression; the concept knowledge expression is a predicate expression of a concept object corresponding to each device to be diagnosed; the relation knowledge expression is the attribute expression of the concept object corresponding to each device to be diagnosed and the relation expression between the attribute expressions.
Expressing concept knowledge: the type knowledge expression is description of concept objects, and a corresponding predicate is established for each concept object corresponding to each to-be-diagnosed in a power grid for knowledge expression, as shown in fig. 3, for example, predicate Bus represents a Bus class, that Bus (x) represents that device x is a Bus, in order to improve reusability of knowledge expression, an object-oriented method is adopted to define a nested relationship between classes, where parent classes and subclasses have inheritance characteristics, such as Bus (x) or Primary _ equivalent (x), i.e., Primary devices.
Specifically, in an example, as shown in fig. 4, the step of establishing knowledge expression between concept objects corresponding to devices to be diagnosed based on first-order predicate logic includes the steps of:
step S410, carrying out hierarchical classification on the concept objects corresponding to the equipment to be diagnosed according to the equipment grade and the equipment type;
step S420, defining corresponding predicate expressions for the concept objects after hierarchical classification by using an object-oriented method, and generating concept knowledge expressions;
and step S430, expressing the attributes of the concept objects corresponding to the devices to be diagnosed and the relationship between the concept objects based on the concept knowledge expression, and performing one-to-one corresponding constraint on the relationship between the predicate expressions according to different types of the devices to be diagnosed to generate the relationship knowledge expression.
It should be noted that the relationship between objects is a basis for forming facts, and for conceptual objects corresponding to devices to be diagnosed in a power grid, the power grid fault diagnosis method hierarchically classifies the conceptual objects based on summary analysis, defines corresponding predicate expressions by using an object-oriented method, declares class dependencies among the conceptual objects, forms atomic knowledge of fault diagnosis, analyzes and extracts the relationship among the conceptual objects, and constrains the predicate expressions according to different types of objects in the relationship. And the expression of knowledge in fault diagnosis is realized through the definition of the relation predicate and the concept predicate.
Expressing the relation knowledge: in addition to the expression of concept knowledge describing concept objects, the attributes of the concept objects in these power grids and the relationships between them need to be explained, and this kind of knowledge is defined as the expression of relationship knowledge in this application, wherein the expression of relationship knowledge mainly includes two types: a single conceptual object and its corresponding operational data, i.e., object-data relationships; relationships between multiple conceptual objects, i.e., object-object relationships; the following is a detailed description:
object-data relationship: the method comprises the following steps that a large amount of operation data are associated with equipment to be diagnosed in a power grid, data information consisting of numerical values or character strings reflects the operation state of the equipment to be diagnosed in the power grid, such as the current value of a line, the opening and closing state of a switch, the voltage level of the equipment and the like, and corresponding relational predicates are established to explain the relations; as shown in table 1, for example, current _ value (y) is 150, which represents that the current value flowing through the primary device y at this time is 150A.
Table 1: object-data relationship table
| Predicate(s) | Object type | Data type | Explaining the meaning |
| Current_Value | Primary_equip | float | Value of current flowing through the device |
| Voltage_Value | Primary_equip | float | Terminal voltage value of equipment |
| Protection_operation | Protection | char | Protection of action situation |
| Breaker_operation | Breaker | char | Operating conditions of the switch |
| Autodevice_operation | Autodevice | char | Operating conditions of the robot |
| Primaryequip_state | Primary_equip | char | Primary equipment state |
| Voltage_level | Primary_equip | int | Primary equipment voltage class |
| Equip_state_change | Primary_equip | char | Change of primary equipment state |
| … | … | … | … |
Object-object relationship: the predicate mainly realizes the description of the relationship between objects, such as the connection relationship between primary equipment, the protection range relationship between protection and the primary equipment, the action relationship between protection and a breaker, and the like, and the relationship is described by a multi-predicate in the application; the partial relational predicate settings are shown in table 2:
table 2: object-data relationship table
And S220, expressing the logic between knowledge expressions based on the first-order predicate logic to obtain a preset fault judgment rule.
It should be noted that, when a fault occurs in the power grid, different primary and secondary device types within a fault range and different association relationships among the devices generate different action responses, that is, action logics among the devices after the fault occurs; the action logics form the criterion of fault diagnosis, and the action logics are expressed by means of the strong description capacity of first-order predicate logic on complex logics based on the knowledge expression method of fault diagnosis to form the rule expression of fault diagnosis.
Specifically, in one example, the step of expressing the logic between knowledge expressions based on the first-order predicate logic to obtain the preset fault judgment rule includes the steps of:
and performing if-then structural rule expression by taking the concept knowledge expression and the relation knowledge table as a drive based on the logic connection words, the limiting quantifier and the user-defined variables in the first-order predicate logic to obtain a preset fault judgment rule.
It should be noted that, driven by the concept knowledge expression and the relationship knowledge expression, the rule expression of the if-then structure is defined by using the logic connection words, the limiting quantifier words and the custom variable description in the first-order predicate logic, and the rule described based on the first-order predicate logic can express a more complex logic relationship, so that the generality is higher.
In a specific application, in order to realize the judgment of the fault cause by using the rule, the fault judgment rule in the application mainly expresses the logic relations among protection and equipment, protection and protection, and protection and switch through logic constraints, and the corresponding rule is as follows: (where exists is a restricted quantifier, x, y, z are custom variables, &, | correspond to logical conjunction symbols with, OR, NOT, and implication)
Protection and equipment: constraints that protect the relationship with the devices it protects, such as:
protection and switching: the action relationship constraint between the protection and action switch, for example:
protection and protection the action logic between the protection, for example:
and reasoning the contents in the fact database based on a preset fault judgment rule, and continuously reasoning new facts and corresponding explanations until the new facts are not generated, so that the reasoning is complete. As shown in fig. 5, the specific steps are:
step S510, updating the fact database by using the last new fact;
step S520, invoking a preset fault judgment rule to infer contents in the updated fact database, and obtaining a new fact and a corresponding explanation next time until no new fact is formed.
It should be noted that after each inference, if a new fact is obtained, the obtained new fact is added to the fact database, the fact database is updated, and the next inference is performed. In one case, if the last new fact is the operation to be executed, the operation to be executed is completed; and updating the fact database by using the last new fact after the operation to be executed is completed. For example, when the obtained new fact is an operation that requires a function to be called to perform a related operation, the function needs to be called first to complete the related operation, and the new fact that completes the related operation is added to the fact database, so that the database is updated.
And step S140, outputting the new facts and the corresponding explanations in sequence according to the acquisition order when the reasoning is finished, and determining a diagnosis result according to each new fact and the corresponding explanation.
It should be noted that after reasoning is completed on the fault feature information based on the preset judgment rule, the new facts and the corresponding interpretations are output according to the obtained sequence, and all the obtained new facts and corresponding interpretations are diagnosis results.
In order to better understand the method for intelligently diagnosing the grid fault of the present application, an application of the present application to a station a of a 110kV (kilovolt) substation (the topology structure of which is shown in fig. 6 below) is taken as an example for description (the processing flow is shown in fig. 7):
when a #1 main transformer in the existing station breaks down, receiving a remote signaling message as follows;
total station accident action at 2017/07/3022: 21: 00A station
2017/07/3022: 21: 00A station #1 main transformer differential protection action
2017/07/3022: 21: 00A station #1 main transformer low 501 switch accident trip off
2017/07/3022: 21: 01A station 10kV bus coupler 500A spare power automatic switching device action
2017/07/3022: 21: 01A station 10kV bus coupler 500A opening and closing device
1) After the system receives the alarm message, firstly reading the alarm message line by line through keywords to generate accident characteristic information expressed in a first-order predicate form, and the method comprises the following steps:
differential _ protection (#1 main transformer Differential protection)
Protect _ equip (#1 main transformer differential protection, #1 main transformer)
Protection _ operation (#1 main transformer differential Protection) ═ operation
Breaker _ operation (#1 main transformer low 501 switch) ═ trip
Breaker _ operation (#1 main transformer high-change 102 switch) ═ trip
Automatic operation (10kV bus coupler 500A spare power automatic switching) as action
Breaker _ operation (10kV bus-tie 500A switch) ═ closed
Autodevice _ open _ Breaker (10kV bus coupler 500A spare power automatic switch, 10kV bus coupler 500A switch)
2) Reasoning about causes of faults:
the rule is satisfied:
and (4) conclusion: equip _ fault (#1 main transformer)
3) Outputting a judgment result:
and (3) outputting: the fault equipment is a #1 main transformer
Explanation: #1 Main Transformer differential protection action, Main Transformer high 102 switch, Main Transformer low 101 switch trip, judge as the main Transformer trouble.
The case successfully infers and judges the fault reason through the fault judging method;
in each embodiment of the power grid fault intelligent diagnosis method, a remote signaling message reported by each device to be diagnosed in a power grid is received; reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; calling a preset fault judgment rule in a rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; when reasoning is finished, new facts and corresponding explanations are sequentially output according to the obtaining sequence, a diagnosis result is determined according to the new facts and the corresponding explanations, a preset fault judgment rule is obtained through rule expression of the relation between the devices to be diagnosed formed in advance based on first-order predicate logic, logic reasoning is carried out on fault characteristic information in a remote communication message, the new facts and the corresponding explanations are obtained, the diagnosis result is obtained according to the new facts and the corresponding explanations, and therefore accuracy of fault diagnosis is improved.
Furthermore, an object-oriented architecture is applied, power grid objects are described in a conceptualization mode, and knowledge expression of relationships among the conceptualized objects is provided; and defining a first-order predicate set of related primary and secondary equipment attributes and relation description suitable for power grid fault judgment according to the characteristics of different relations. The proposed expression method is highly versatile and maintainable. A first-order predicate logic description framework of action logics of various primary and secondary devices under different power grid faults is established. And a fault judgment rule under first-order predicate logic is formulated on the basis of the incidence relation between the equipment action and the alarm information. The proposed rule can describe the fault condition sufficiently and accurately, and the fault rapid reasoning is realized.
It should be understood that although the steps in the flowcharts of fig. 1, 2, 4, 5, and 7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1, 2, 4, 5, and 7 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 8, there is provided a grid fault intelligent diagnosis apparatus, including:
the message receiving module 81 is configured to receive a remote signaling message reported by each device to be diagnosed in the power grid;
a fact database forming module 83, configured to read fault feature information in the remote communication message, and confirm the fact database according to the fault feature information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed;
the reasoning module 85 is used for calling a preset fault judgment rule in the rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression of the relation between the devices to be diagnosed formed on the basis of first-order predicate logic;
and a conclusion output module 87, configured to output the new facts and the corresponding interpretations in sequence according to the acquisition order when the inference is completed, and determine a diagnosis result according to each new fact and the corresponding interpretation.
For specific limitations of the power grid fault intelligent diagnosis device, reference may be made to the above limitations of the power grid fault intelligent diagnosis method, and details are not described here. All or part of each module in the power grid fault intelligent diagnosis device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing remote signaling messages, preset judgment rules, fault characteristic information, new facts and corresponding explanations. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method for intelligent diagnosis of grid faults.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
receiving remote signaling messages reported by each device to be diagnosed in the power grid;
reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed;
calling a preset fault judgment rule in a rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression of the relation between the devices to be diagnosed formed on the basis of first-order predicate logic;
and when the reasoning is finished, sequentially outputting the new facts and the corresponding explanations according to the acquisition sequence, and determining a diagnosis result according to each new fact and the corresponding explanations.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
establishing knowledge expression between concept objects corresponding to the equipment to be diagnosed based on first-order predicate logic;
and expressing the logic between the knowledge expressions based on the first-order predicate logic to obtain a preset fault judgment rule.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out hierarchical classification on the concept objects corresponding to the equipment to be diagnosed according to the equipment grade and the equipment type;
defining corresponding predicate expressions for the concept objects after hierarchical classification by using an object-oriented method, and generating concept knowledge expressions;
expressing the attribute of the concept object corresponding to each device to be diagnosed and the relation between the attribute and the relation based on the concept knowledge expression, and carrying out one-to-one corresponding constraint on the relation between predicate expressions according to different types of the devices to be diagnosed to generate the relation knowledge expression.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
updating the fact database by using the last new fact;
and calling a preset fault judgment rule to infer the content in the updated fact database, and acquiring a new fact and a corresponding explanation at the next time until no new fact is formed.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
if the last new fact is the operation to be executed, the operation to be executed is completed;
and updating the fact database by using the last new fact after the operation to be executed is completed.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving remote signaling messages reported by each device to be diagnosed in the power grid;
reading fault characteristic information in the remote communication message, and confirming a fact database according to the fault characteristic information; the fault characteristic information comprises concept objects, state types and operation data corresponding to the equipment to be diagnosed;
calling a preset fault judgment rule in a rule database to reason the content in the fact database, and acquiring a new fact and a corresponding explanation; the preset fault judgment rule is a rule expression of the relation between the devices to be diagnosed formed on the basis of first-order predicate logic;
and when the reasoning is finished, sequentially outputting the new facts and the corresponding explanations according to the acquisition sequence, and determining a diagnosis result according to each new fact and the corresponding explanations.
In one embodiment, the computer program when executed by the processor further performs the steps of:
establishing knowledge expression between concept objects corresponding to the equipment to be diagnosed based on first-order predicate logic;
and expressing the logic between the knowledge expressions based on the first-order predicate logic to obtain a preset fault judgment rule.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out hierarchical classification on the concept objects corresponding to the equipment to be diagnosed according to the equipment grade and the equipment type;
defining corresponding predicate expressions for the concept objects after hierarchical classification by using an object-oriented method, and generating concept knowledge expressions;
expressing the attribute of the concept object corresponding to each device to be diagnosed and the relation between the attribute and the relation based on the concept knowledge expression, and carrying out one-to-one corresponding constraint on the relation between predicate expressions according to different types of the devices to be diagnosed to generate the relation knowledge expression.
In one embodiment, the computer program when executed by the processor further performs the steps of:
updating the fact database by using the last new fact;
and calling a preset fault judgment rule to infer the content in the updated fact database, and acquiring a new fact and a corresponding explanation at the next time until no new fact is formed.
In one embodiment, the computer program when executed by the processor further performs the steps of:
if the last new fact is the operation to be executed, the operation to be executed is completed;
and updating the fact database by using the last new fact after the operation to be executed is completed.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the claims. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910952727.2A CN110646710B (en) | 2019-10-09 | 2019-10-09 | Power grid fault intelligent diagnosis method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910952727.2A CN110646710B (en) | 2019-10-09 | 2019-10-09 | Power grid fault intelligent diagnosis method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110646710A CN110646710A (en) | 2020-01-03 |
| CN110646710B true CN110646710B (en) | 2021-08-31 |
Family
ID=69012388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910952727.2A Active CN110646710B (en) | 2019-10-09 | 2019-10-09 | Power grid fault intelligent diagnosis method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110646710B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112187526B (en) * | 2020-09-14 | 2023-04-07 | 广东电网有限责任公司广州供电局 | Complex fault diagnosis method and device for power grid dispatching and computer equipment |
| CN114089253A (en) * | 2021-10-28 | 2022-02-25 | 国网天津市电力公司电力科学研究院 | Electromagnetic pouring type voltage transformer fault early warning device and method |
| CN114492807B (en) * | 2022-02-10 | 2024-11-19 | 杭州和利时自动化有限公司 | A method, device and system for realizing generative reasoning based on knowledge graph |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0813166B2 (en) * | 1992-03-26 | 1996-02-07 | 関西電力株式会社 | Driving assistance device for substation |
| CN101004799A (en) * | 2007-01-16 | 2007-07-25 | 中山大学 | Tense generation formula system |
| CN101266279A (en) * | 2008-05-09 | 2008-09-17 | 东北大学 | A power grid fault diagnosis device and method |
| US7536370B2 (en) * | 2004-06-24 | 2009-05-19 | Sun Microsystems, Inc. | Inferential diagnosing engines for grid-based computing systems |
| CN104459474A (en) * | 2014-12-22 | 2015-03-25 | 国网上海市电力公司 | Intelligent distribution network fault recognition method |
| CN110086166A (en) * | 2019-04-04 | 2019-08-02 | 中国电力科学研究院有限公司 | A kind of representation method and system of power grid operation limit |
-
2019
- 2019-10-09 CN CN201910952727.2A patent/CN110646710B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0813166B2 (en) * | 1992-03-26 | 1996-02-07 | 関西電力株式会社 | Driving assistance device for substation |
| US7536370B2 (en) * | 2004-06-24 | 2009-05-19 | Sun Microsystems, Inc. | Inferential diagnosing engines for grid-based computing systems |
| CN101004799A (en) * | 2007-01-16 | 2007-07-25 | 中山大学 | Tense generation formula system |
| CN101266279A (en) * | 2008-05-09 | 2008-09-17 | 东北大学 | A power grid fault diagnosis device and method |
| CN104459474A (en) * | 2014-12-22 | 2015-03-25 | 国网上海市电力公司 | Intelligent distribution network fault recognition method |
| CN110086166A (en) * | 2019-04-04 | 2019-08-02 | 中国电力科学研究院有限公司 | A kind of representation method and system of power grid operation limit |
Non-Patent Citations (1)
| Title |
|---|
| 基于分层模型配电网结构知识表示的拓扑分析方法;袁建刚等;《南方电网技术》;20091220;第3卷(第6期);正文第95-99页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110646710A (en) | 2020-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110646710B (en) | Power grid fault intelligent diagnosis method, device, computer equipment and storage medium | |
| CN110059356A (en) | A kind of bulk power grid intelligent control system and method based on big data and artificial intelligence | |
| CN101833324B (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN109993443B (en) | A spatio-temporal situational awareness model mining method for power grid equipment operation status | |
| CN107016507A (en) | Electric network fault method for tracing based on data mining technology | |
| CN111474444B (en) | Line fault power restoration decision method based on knowledge graph | |
| CN110210632A (en) | Failure emergency processing method, device and terminal based on ubiquitous electric power Internet of Things | |
| CN106485594A (en) | A kind of main distribution integration incident response decision method | |
| CN114661905A (en) | Power grid fault diagnosis method based on BERT | |
| CN118964900B (en) | Causal knowledge guidance-based power equipment fault diagnosis method and causal knowledge guidance-based power equipment fault diagnosis system | |
| CN109445411A (en) | A kind of Substation fault diagnosis | |
| Huang et al. | An intelligent system for advanced dynamic security assessment | |
| CN116383681A (en) | Transformer running state prediction method based on long-term and short-term memory network | |
| Ding et al. | A review of the construction and application of knowledge graphs in smart grid | |
| CN120258774A (en) | A method for constructing a health status diagnosis framework for power main equipment based on adversarial learning | |
| Teng et al. | On-line fault diagnosis technology and application based on deep learning of fault characteristic of power grid | |
| Zhang et al. | Research on data-driven model for power grid fault diagnosis fusing topological quantification information | |
| Yin et al. | Fault diagnosis based on fault tree and Bayesian network for pure electric trucks | |
| Liu et al. | Design of equipment condition maintenance knowledge base in power IoT based on edge computing | |
| CN115834406A (en) | A Convolutional Neural Network Based Transient Stability Prediction Method for Power Grids | |
| Li et al. | A Knowledge Extraction System Based on Weight Optimization Applied and Evaluated to Distribution Network Fault Assistant Decision | |
| Gong et al. | Motor fault diagnosis based on decision tree-Bayesian network model | |
| He et al. | Study on the system method of DCS remote operation and maintenance system of nuclear power plant based on parallel theory | |
| Ning | Comparison of several common intelligent fault diagnosis knowledge-based method under nonlinear small sample conditions | |
| CN113472078B (en) | Method for visual monitoring equipment based on neural network technology |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200923 Address after: 510620 Tianhe District, Guangzhou, Tianhe South Road, No. two, No. 2, No. Applicant after: Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd. Address before: 510620 Tianhe District, Guangzhou, Tianhe South Road, No. two, No. 2, No. Applicant before: GUANGZHOU POWER SUPPLY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |