CN112699171A - Vehicle alarm data knowledge graph construction method and related device - Google Patents
Vehicle alarm data knowledge graph construction method and related device Download PDFInfo
- Publication number
- CN112699171A CN112699171A CN202011640728.2A CN202011640728A CN112699171A CN 112699171 A CN112699171 A CN 112699171A CN 202011640728 A CN202011640728 A CN 202011640728A CN 112699171 A CN112699171 A CN 112699171A
- Authority
- CN
- China
- Prior art keywords
- alarm data
- data
- vehicle
- vehicle alarm
- type
- 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.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000004590 computer program Methods 0.000 claims description 10
- 230000001364 causal effect Effects 0.000 claims description 5
- 239000000523 sample Substances 0.000 claims description 4
- 238000009412 basement excavation Methods 0.000 abstract description 6
- 238000001228 spectrum Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000005065 mining Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000009411 base construction Methods 0.000 description 3
- 239000000969 carrier Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 241001415395 Spea Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application discloses a vehicle alarm data knowledge map construction method and a related device, aiming at multi-class vehicle alarm data, wherein the association relationship of the alarm data of different classes may exist in the combination of the alarm data of different classes, in order to find the association relationship of the alarm data of different classes, a multi-objective optimization model can be established according to the combination of the alarm data of different classes, and the established multi-objective optimization model is solved according to a multi-objective evolutionary algorithm to determine the association relationship of the alarm data of different classes, therefore, the multi-objective optimization model is established, the multi-objective evolutionary algorithm is utilized to carry out optimization, the association relationship existing among the alarm data of the multi-class vehicles can be automatically excavated, the excavation process is time-saving and labor-saving, the excavation efficiency is improved, and meanwhile, the association relationship among the alarm data of the multi-class vehicles is shown by adopting a known spectrum mode, visual basis can be better provided for follow-up alarm fault analysis.
Description
Technical Field
The invention relates to the technical field of big data processing, in particular to a vehicle alarm data knowledge graph construction method and a related device.
Background
With the development of science and technology, after a vehicle becomes a main transportation tool in people's life, people also put forward higher requirements on the safety of the vehicle, and hope that the vehicle fault can be early warned before the vehicle goes wrong.
At present, a fault early warning mode generally includes inputting vehicle data into an algorithm model, training the algorithm model to enable the algorithm model to learn characteristics of the vehicle data, and then predicting whether the vehicle data can have faults or not through the trained algorithm model. However, this method is only capable of predicting vehicle data, and cannot mine the correlation between vehicle data from the vehicle data, and therefore cannot find the cause of a vehicle failure, and is poor in interpretability.
Disclosure of Invention
In order to solve the problems, the application provides a vehicle alarm data knowledge graph construction method and a related device, which are used for mining the relevance between vehicle alarm data so as to explain the reasons of vehicle faults.
The application provides a vehicle alarm data knowledge graph construction method in a first aspect, and the method comprises the following steps:
acquiring alarm data of various vehicles;
establishing a multi-objective optimization model according to the combination of the alarm data of different types of vehicles in the alarm data of the multiple types of vehicles;
solving the multi-target optimization model according to a multi-target evolutionary algorithm, and determining the incidence relation of the alarm data of the vehicles of different types;
and constructing a vehicle alarm data knowledge graph according to the incidence relation.
Optionally, the multiple types of vehicle alarm data include a first type of data and a second type of data, and the establishing of the multi-objective optimization model according to the combination of the different types of vehicle alarm data in the multiple types of vehicle alarm data includes:
establishing a multi-objective optimization model by taking confidence and promotion degrees as targets according to the combination of different types of vehicle alarm data in the multi-type vehicle alarm data; the confidence coefficient is the probability that the first type of data also presents an alarm state under the condition that the second type of data presents the alarm state, and the promotion degree is the degree of association between the first type of data and the second type of data.
Optionally, the establishing a multi-objective optimization model with the confidence and the lifting degree as the target includes:
establishing a multi-objective optimization model by taking the support degree, the confidence degree and the promotion degree as targets; and the support degree is the frequency of the first type data and the second type data presenting alarm states at the same time.
Optionally, the encoding mode of the multi-objective evolutionary algorithm is as follows:
each type of vehicle alarm data in the multiple types of vehicle alarm data is represented by two-bit codes, wherein the first-bit codes identify the combination relationship between the vehicle alarm data of the type in which the vehicle alarm data is located and the vehicle alarm data of other types, and the second-bit codes identify the causal relationship between the vehicle alarm data of the type in which the vehicle alarm data is located and the vehicle alarm data of other types.
Optionally, the solving the multi-objective optimization model according to the multi-objective evolutionary algorithm to determine the incidence relation of the alarm data of the different types of vehicles includes:
and in the process of solving the multi-objective optimization model according to a multi-objective evolutionary algorithm, determining the incidence relation of the alarm data of the different types of vehicles by adopting alpha domination control domination weight.
Optionally, the association relationship between the different types of vehicle alarm data is an association relationship between one type of vehicle alarm data and another type of vehicle alarm data.
Optionally, the vehicle alarm data includes at least two of charging state alarm data, cell voltage alarm data, single probe temperature alarm data, battery pack voltage alarm data, driving motor temperature alarm data, driving motor speed alarm data, and motor controller temperature alarm data.
The second aspect of the present application provides a vehicle alarm data knowledge base constructing apparatus, the apparatus comprising: the system comprises an acquisition unit, an establishing unit, a solving unit and a display unit;
the acquisition unit is used for acquiring alarm data of various vehicles;
the establishing unit is used for establishing a multi-objective optimization model according to the combination of different types of vehicle alarm data in the multi-type vehicle alarm data;
the solving unit is used for solving the multi-objective optimization model according to a multi-objective evolutionary algorithm and determining the incidence relation of the alarm data of the vehicles of different types;
and the display unit is used for constructing a vehicle alarm data knowledge graph according to the incidence relation.
A third aspect of the present application provides a vehicle alert data knowledge map construction apparatus, the apparatus comprising a processor and a memory:
the memory is used for storing a computer program and transmitting the computer program to the processor;
the processor is configured to perform the method of the first aspect according to instructions in the computer program.
A fourth aspect of the present application provides a computer-readable storage medium for storing a computer program for performing the method of the first aspect described above.
Compared with the prior art, the technical scheme of the application has the advantages that:
according to the technical scheme, aiming at the alarm data of the vehicles of various types, the association relationship of the alarm data of the vehicles of various types may exist in the combination of the alarm data of the vehicles of various types, in order to find the association relationship of the alarm data of the vehicles of various types, can establish a multi-objective optimization model according to the combination of the alarm data of different types of vehicles, solve the established multi-objective optimization model according to a multi-objective evolutionary algorithm to determine the incidence relation of the alarm data of different types of vehicles, therefore, by constructing a multi-objective optimization model and utilizing a multi-objective evolutionary algorithm to carry out optimization, the incidence relation among the alarm data of various vehicles can be automatically excavated, the excavation process is time-saving and labor-saving, the excavation efficiency is improved, meanwhile, the incidence relation among the alarm data of the vehicles of multiple types is displayed in a spectrum learning and recognizing mode, so that a visual basis can be better provided for the follow-up alarm fault analysis.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a vehicle alarm data knowledge base construction method provided by an embodiment of the application;
fig. 2 is a schematic diagram of an encoding method according to an embodiment of the present application;
FIG. 3 is a schematic illustration of a vehicle warning data knowledge map provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of a vehicle alarm data knowledge base constructing device according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a vehicle alarm data knowledge base construction device according to an embodiment of the application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The causes of vehicle failure are presented in a variety, sophistication, randomization, etc., and vehicle failure is generally not related to a single factor alone, but rather a combination of factors that manifest as one or more failures. That is, there is often a correlation between vehicle warning data. The method of the algorithm model cannot mine the incidence relation between the vehicle data from the vehicle data, so that the reason of the vehicle fault cannot be found, and the interpretability is poor.
In order to mine the relevance among different types of vehicle alarm data and to be used for subsequent analysis of specific fault reasons, the technology of adding semantic labels or corpus participles to the vehicle alarm data is generally adopted in the related technology for analyzing mass vehicle alarm data, and then the mining of the relevance among the data is realized in a matching mode.
For example, by establishing a plurality of entity word lists in advance, and mining entities from various vehicle alarm data in a word list matching mode; and then, technical personnel manually review and label the attribute relationship among the entities, thereby mining the association relationship among the entities. However, for the vehicle alarm data, the number of the vehicle alarm data is large, and the types of the vehicle alarm data are large, and the process of mining the multiple types of vehicle alarm data by adopting the technical scheme cannot be automatically performed, so that the mining process is time-consuming and labor-consuming, and the mining efficiency is low.
Based on the method and the device, the association relation between the alarm data of different types of vehicles can be automatically mined.
Referring to fig. 1, fig. 1 is a flowchart of a vehicle alarm data knowledge graph construction method provided by an embodiment of the present application, which may include the following steps 101-104.
S101: and acquiring various types of vehicle alarm data.
The category of the vehicle alarm data is not specifically limited in the present application, and for example, the vehicle alarm data may be state of charge (SOC) alarm data, cell voltage alarm data, single probe temperature alarm data, battery pack voltage alarm data, driving motor temperature alarm data, driving motor rotation speed alarm data, motor controller temperature alarm data, or the like.
For example, the vehicle alarm data may be two types of vehicle alarm data, or may also be three types of vehicle alarm data, and this is not specifically limited in this application.
The embodiment of the present application does not specifically limit the manner of obtaining data, for example, vehicle alarm data may be obtained from an automobile monitoring platform, and the obtained data may be in the form of a table. As shown in table 1.
TABLE 1
|
Vehicle alarm data 2 | ······ | Vehicle alarm data N |
True | False | ······ | True |
······ | ······ | ······ | ······ |
True | True | ······ | True |
In table 1, there are N types of vehicle alarm data, which are represented by vehicle alarm data 1, vehicle alarm data 2, vehicle alarm data N, and the like, and in each type of vehicle alarm data, there are M pieces of data (the head of the table is removed in table 1, there are M pieces of vehicle alarm data in common). Wherein True represents that the vehicle alarm data of the type present an alarm state, and False represents that the vehicle alarm data of the type present an unalarmed state. Taking the vehicle alarm data 1 as an example, the first row of data of the vehicle alarm data 1 is data showing an alarm state, and the mth row of data of the vehicle alarm data 1 is data showing an unalarmed state.
It should be noted that, in order to facilitate automatic identification, the type of the vehicle alarm data may be converted into a boolean type, for example, 1 indicates that the vehicle alarm data of this type is in an alarm state, and 2 indicates that the vehicle alarm data of this type is not in an alarm state, so as to facilitate automatic subsequent mining of the association between the vehicle alarm data of different types.
S102: and establishing a multi-objective optimization model according to the combination of the alarm data of different types of vehicles in the alarm data of the multiple types of vehicles.
The alarm data of different types of vehicles may have an association relationship, taking three types of vehicle alarm data as an example, the three types of vehicle alarm data are respectively vehicle alarm data A, vehicle alarm data B and vehicle alarm data C, and the association relationship possibly existing among the three types of vehicle alarm data may be: when the vehicle alarm data A is in an alarm state, the vehicle alarm data B is in an alarm state, when the vehicle alarm data A is in an alarm state, the vehicle alarm data C is in an alarm state, when the vehicle alarm data B is in an alarm state, the vehicle alarm data A is in an alarm state, when the vehicle alarm data B is in an alarm state, the vehicle alarm data C is in an alarm state, when the vehicle alarm data A and the vehicle alarm data B are in alarm states at the same time, the vehicle alarm data C is in an alarm state, and the like, which are not exemplified in any more.
As a possible implementation manner, the association relationship of the alarm data of different types of vehicles is the association relationship between the alarm data of one type of vehicles and the alarm data of another type of vehicles, so that the association relationship of the alarm data of multiple types of vehicles can be more clearly represented by a knowledge graph constructed subsequently. For another example, the association relationship between the different types of vehicle alarm data is an association relationship between two types of vehicle alarm data and a third type of vehicle alarm data, which is not specifically limited in this application.
The combination of the alarm data of different types of vehicles represents the possible association relationship before the alarm data of different types of vehicles, for example, when the alarm data A of the vehicle is in the alarm state, the alarm data B of the vehicle is in the alarm state, and the fault corresponding to the alarm data B of the vehicle may be caused after the fault corresponding to the alarm data A of the vehicle occurs.
It should be noted that, a fault corresponding to the vehicle alarm data a may also cause a fault corresponding to the vehicle alarm data B to occur, and a fault corresponding to the vehicle alarm data B may also cause the same fault or different faults to occur, which is not specifically limited in this application.
The method for establishing the multi-objective optimization model is not particularly limited in the application, for example, the multi-objective model established by two targets, for example, the targets can be confidence degrees and promotion degrees according to the combination of different types of vehicle alarm data in the multiple types of vehicle alarm data. The multi-objective model may also be a model built from three objectives, for example, the objectives may support, confidence, and lift. Three objects will be described as an example.
For convenience of explanation, the following description will be given taking the example that the plurality of types of vehicle alarm data include the first type of data and the second type of data, and it is understood that the first type of data and the second type of data are different types of vehicle alarm data. For convenience of description, the following description will be given taking an example in which the first-type data and the second-type data respectively include 1 type of vehicle alarm data.
The first target is: and (4) supporting degree.
The support degree is the frequency of the first class data and the second class data presenting alarm states at the same time, and is shown in formula (1).
Wherein, a represents the first kind of data, C represents the second kind of data, Sup (a → C) represents the support degree of a and C, and M represents the data amount of the vehicle alarm data therein, it can be understood that the data amount of each kind of vehicle alarm data is the same, the number of the combination of the a kind of vehicle alarm data and the C kind of vehicle alarm data is the same as the number of the combination of the a kind of vehicle alarm data and the B kind of vehicle alarm data, and the total number is M. n (ac) represents the frequency of occurrence of alarm states in both a and C in the vehicle alarm data consisting of a and C.
For convenience of explanation, the following description is made with reference to table 2.
TABLE 2
|
Vehicle alarm data 2 | Vehicle alarm data 3 |
True | False | True |
True | True | True |
False | False | False |
Where M is 3, a is vehicle alarm data 1, C is vehicle alarm data 2, and the number of rows 3 of data in which a and C both correspond to True is 1, the support degrees of a and C are shown in formula (2).
The frequency of the first-class data and the second-class data which are in the alarm state at the same time can be evaluated through the support degree, and the higher the frequency is, the more the occurrence frequency of the situation that the corresponding fault of the vehicle alarm data A may cause the corresponding fault of the vehicle alarm data B to occur after the corresponding fault of the vehicle alarm data A occurs is shown.
And a second target: and (4) supporting degree.
The confidence is the probability that the first type of data will also present an alarm state if the second type of data is present, see equation (3).
Wherein Conf (A → C) represents the confidence of A and C, Sup (AC) is a shorthand form of Sup (A → C) and represents the support degree of A and C, and Sup (A) represents the support degree of A.
Continuing with the example of Table 2, if vehicle alert data 1 corresponds to a True number of 2 in the 3 rows of data, then the confidence levels for A and C are given in equation (4).
The degree of association of the association relationship between the first type of data and the second type of data can be evaluated through the confidence. For example, the first kind of data often presents an alarm state, but when the first kind of data presents an alarm state, the probability that the second kind of data presents an alarm state is 50%, and although the support degree of the first kind of data and the second kind of data is high, the confidence degree is not high, which means that the association degree of the first kind of data and the second kind of data is not high enough for analyzing the fault cause.
And a third target: the degree of lift.
The degree of lift is the degree of association between the first class of data and the second class of data, see equation (5).
In this case, Lift (A → C) represents the Lift of A and C, and Sup (C) represents the support of C.
The range of the degree of lift is [0,. varies ]), where a value of the degree of lift smaller than 1 indicates that the association between the first type of data and the second type of data is in a negative correlation, and a value of the degree of lift larger than 1 indicates that the association between the first type of data and the second type of data is in a positive correlation. For example, the embodiment of the application may only consider a case that the association relationship between the first type of data and the second type of data shows positive association, and a larger numerical value indicates that the degree of association between the first type of data and the second type of data is higher.
Continuing with Table 2 as an example, the degree of lift for A and C is given in equation (6).
Whether the incidence relation between the first type data and the second type data is effective or not can be represented through the promotion degree. For example, the probability that the first type of data presents an alarm state under the condition that the second type of data presents an alarm state is 0.8, the probability that the second type of data presents an alarm state in the data volume is 0.8, that is, the promotion degree of the first type of data and the second type of data is 1, and the first type of data and the second type of data are independent of each other. That is, although the confidence degrees of the first type data and the second type data are high, the promotion degrees of the first type data and the second type data are low, and thus, a combination that a fault corresponding to the vehicle alarm data a may cause a fault corresponding to the vehicle alarm data B to also occur after the fault corresponding to the vehicle alarm data a occurs may not occur in practice, and is an invalid combination.
If the confidence and the promotion degree of the first-class data and the second-class data are high, the fault reason can be further analyzed according to the condition that the fault corresponding to the vehicle alarm data B may occur after the fault corresponding to the vehicle alarm data A occurs. If the confidence degree and the promotion degree of the first-class data and the second-class data are both high and the support degree of the first-class data and the second-class data is also high, it is indicated that the situation that the fault corresponding to the vehicle alarm data B may occur frequently after the fault corresponding to the vehicle alarm data A occurs, and the fault can be preferentially analyzed.
S103: and solving the multi-objective optimization model according to a multi-objective evolutionary algorithm to determine the incidence relation of the alarm data of the vehicles of different types.
The present application does not specifically limit The kind of multi-objective evolution Algorithm (MOEA), for example, a Non-dominated sorting genetic Algorithm with elite strategy (NSGA-II), an intensity Pareto evolution Algorithm (The Strength Pareto evolution Algorithm, SPEA), and The like.
The multi-objective evolutionary algorithm can be realized by adopting the existing open source software, such as MATLAB, or a Python algorithm toolbox.
The embodiment of the present application does not specifically limit the encoding method adopted by the multi-objective algorithm, and an encoding method is introduced below with reference to the accompanying drawings.
Referring to fig. 2, the figure is a schematic diagram of an encoding method provided in the embodiment of the present application. In fig. 2, a total of class D vehicle alarm data are respectively represented as Item1, Item2, … and Item, where each class of vehicle alarm data is represented by a two-bit code, the first code identifies the combination relationship between the vehicle alarm data of the class and the vehicle alarm data of other classes, for example, 1 indicates that the two classes of vehicle alarm data have a combination relationship, and the second code identifies the causal relationship between the vehicle alarm data of the class and the vehicle alarm data of other classes, for example, 1 indicates that the two classes of vehicle alarm data have a causal relationship. For example, if the first bit encoding of Item1 is 1 and the first bit encoding of Item3 is 1, the current bar encoding corresponds to the combination relationship between Item1 and Item3, the first bit encoding of Item1 is 0 and the first bit encoding of Item3 is 1, and the failure corresponding to Item1 may occur after the failure corresponding to Item3 occurs in the bar encoding shown in fig. 2.
As a possible implementation manner, as the vehicle alarm data categories increase, the number of finally obtained non-dominated solutions may also be larger, which is not beneficial to subsequent analysis, and in order to reduce the number of non-dominated solutions, in the process of solving the multi-objective optimization model according to the multi-objective evolutionary algorithm, alpha domination (c) may be adoptedDominant) controlling dominant weights, e.g. controllingAnd the dominated angle is reduced, so that the number of non-dominated solutions is reduced, and the non-dominated solutions are used as the incidence relation of alarm data of different types of vehicles.
S104: and constructing a vehicle alarm data knowledge graph according to the association relation.
Knowledge map (Knowledge Graph) is a series of different graphs displaying Knowledge development process and structure relationship in the book intelligence field, describing Knowledge resources and carriers thereof by using visualization technology, mining, analyzing, constructing, drawing and displaying Knowledge and mutual relation between Knowledge resources and Knowledge carriers.
A knowledge graph may consist of a single piece of knowledge in content, and each piece of knowledge may be represented as a Subject-relationship-Object (SPO) triple. The subject S and the object O are two entities respectively, and P is an attribute relationship between the subject S and the object O. Therefore, by mining all SPO triples, a corresponding knowledge graph can be constructed.
The dominating relationship may be represented as an SPO triplet, e.g., the association of vehicle warning data a with vehicle warning data B is: and when the fault corresponding to the vehicle alarm data A occurs, the fault corresponding to the vehicle alarm data B may also occur, and the SPO triple is represented as { the vehicle alarm data A, and when the fault corresponding to the vehicle alarm data A occurs, the fault corresponding to the vehicle alarm data B may also occur, and the vehicle alarm data B }. The association relationship is constructed as a vehicle alarm data knowledge map as shown in the left diagram of fig. 3, and as the association relationship increases, the vehicle alarm data knowledge map can be as shown in the right diagram of fig. 3.
According to the technical scheme, aiming at the alarm data of the vehicles of various types, the association relationship of the alarm data of the vehicles of various types may exist in the combination of the alarm data of the vehicles of various types, in order to find the association relationship of the alarm data of the vehicles of various types, can establish a multi-objective optimization model according to the combination of the alarm data of different types of vehicles, solve the established multi-objective optimization model according to a multi-objective evolutionary algorithm to determine the incidence relation of the alarm data of different types of vehicles, therefore, by constructing a multi-objective optimization model and utilizing a multi-objective evolutionary algorithm to carry out optimization, the incidence relation among the alarm data of various vehicles can be automatically excavated, the excavation process is time-saving and labor-saving, the excavation efficiency is improved, meanwhile, the incidence relation among the alarm data of the vehicles of multiple types is displayed in a spectrum learning and recognizing mode, so that a visual basis can be better provided for the follow-up alarm fault analysis.
In addition to the method for constructing the vehicle alarm data knowledge graph, the embodiment of the present application also provides a device for constructing the vehicle alarm data knowledge graph, as shown in fig. 4, where the device 400 includes: the system comprises an acquisition unit 401, an establishment unit 402, a solving unit 403 and a display unit 404;
the acquiring unit 401 is configured to acquire multiple types of vehicle alarm data;
the establishing unit 402 is configured to establish a multi-objective optimization model according to a combination of different types of vehicle alarm data in the multiple types of vehicle alarm data;
the solving unit 403 is configured to solve the multi-objective optimization model according to a multi-objective evolutionary algorithm, and determine an association relationship between the alarm data of the different types of vehicles;
the display unit 404 is configured to construct a vehicle alarm data knowledge graph according to the association relationship.
As a possible implementation manner, the multiple types of vehicle alarm data include a first type of data and a second type of data, and the establishing unit 402 is configured to:
establishing a multi-objective optimization model by taking confidence and promotion degrees as targets according to the combination of different types of vehicle alarm data in the multi-type vehicle alarm data; the confidence coefficient is the probability that the first type of data also presents an alarm state under the condition that the second type of data presents the alarm state, and the promotion degree is the degree of association between the first type of data and the second type of data.
As a possible implementation manner, the establishing unit 402 is configured to:
establishing a multi-objective optimization model by taking the support degree, the confidence degree and the promotion degree as targets; and the support degree is the frequency of the first type data and the second type data presenting alarm states at the same time.
As a possible implementation manner, the coding manner of the multi-objective evolutionary algorithm is as follows:
each type of vehicle alarm data in the multiple types of vehicle alarm data is represented by two-bit codes, wherein the first-bit codes identify the combination relationship between the vehicle alarm data of the type in which the vehicle alarm data is located and the vehicle alarm data of other types, and the second-bit codes identify the causal relationship between the vehicle alarm data of the type in which the vehicle alarm data is located and the vehicle alarm data of other types.
As a possible implementation manner, the solving unit 403 is configured to:
and in the process of solving the multi-objective optimization model according to a multi-objective evolutionary algorithm, determining the incidence relation of the alarm data of the different types of vehicles by adopting alpha domination control domination weight.
As a possible implementation manner, the association relationship of the different types of vehicle alarm data is an association relationship between one type of vehicle alarm data and another type of vehicle alarm data.
As a possible implementation manner, the vehicle alarm data includes at least two of charging state alarm data, cell voltage alarm data, single probe temperature alarm data, battery pack voltage alarm data, driving motor temperature alarm data, driving motor rotation speed alarm data, and motor controller temperature alarm data.
The vehicle alarm data knowledge graph construction device provided by the embodiment of the application aims at multi-class vehicle alarm data, wherein incidence relations of the alarm data of different classes may exist in combinations of the alarm data of different classes, in order to find the incidence relations of the alarm data of different classes, a multi-objective optimization model can be established according to the combinations of the alarm data of different classes, the established multi-objective optimization model is solved according to a multi-objective evolutionary algorithm to determine the incidence relations of the alarm data of different classes, therefore, the incidence relations among the alarm data of the multiple classes can be automatically mined by establishing the multi-objective optimization model and utilizing the multi-objective evolutionary algorithm to carry out optimization, the mining process is time-saving and labor-saving, the mining efficiency is improved, and meanwhile, the incidence relations among the alarm data of the multiple classes are shown in a known spectrum mode, visual basis can be better provided for follow-up alarm fault analysis.
The embodiment of the present application further provides a vehicle alarm data knowledge base construction device, referring to fig. 5, which shows a structure diagram of a computer device provided in the embodiment of the present application, and as shown in fig. 5, the device includes a processor 510 and a memory 520:
the memory 510 is used for storing program codes and transmitting the program codes to the processor;
the processor 520 is configured to execute any one of the interface calling methods provided in the above embodiments according to the instructions in the program code.
The embodiment of the application provides a computer-readable storage medium, which is used for storing a computer program, and the computer program is used for executing any one of the vehicle alarm data knowledge graph construction methods provided by the above embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the method embodiment for relevant points. The above-described apparatus embodiments are merely illustrative, and the units and modules described as separate components may or may not be physically separate. In addition, some or all of the units and modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing is directed to embodiments of the present application and it is noted that numerous modifications and adaptations may be made by those skilled in the art without departing from the principles of the present application and are intended to be within the scope of the present application.
Claims (10)
1. A vehicle alarm data knowledge graph construction method is characterized by comprising the following steps:
acquiring alarm data of various vehicles;
establishing a multi-objective optimization model according to the combination of the alarm data of different types of vehicles in the alarm data of the multiple types of vehicles;
solving the multi-target optimization model according to a multi-target evolutionary algorithm, and determining the incidence relation of the alarm data of the vehicles of different types;
and constructing a vehicle alarm data knowledge graph according to the incidence relation.
2. The method of claim 1, wherein the plurality of categories of vehicle alert data include a first category of data and a second category of data, and wherein building the multi-objective optimization model based on a combination of different categories of vehicle alert data in the plurality of categories of vehicle alert data comprises:
establishing a multi-objective optimization model by taking confidence and promotion degrees as targets according to the combination of different types of vehicle alarm data in the multi-type vehicle alarm data; the confidence coefficient is the probability that the first type of data also presents an alarm state under the condition that the second type of data presents the alarm state, and the promotion degree is the degree of association between the first type of data and the second type of data.
3. The method of claim 2, wherein the establishing the multi-objective optimization model with the confidence level and the boost level as the targets comprises:
establishing a multi-objective optimization model by taking the support degree, the confidence degree and the promotion degree as targets; and the support degree is the frequency of the first type data and the second type data presenting alarm states at the same time.
4. The method of claim 1, wherein the multi-objective evolutionary algorithm is encoded in a manner that:
each type of vehicle alarm data in the multiple types of vehicle alarm data is represented by two-bit codes, wherein the first-bit codes identify the combination relationship between the vehicle alarm data of the type in which the vehicle alarm data is located and the vehicle alarm data of other types, and the second-bit codes identify the causal relationship between the vehicle alarm data of the type in which the vehicle alarm data is located and the vehicle alarm data of other types.
5. The method of claim 1, wherein solving the multi-objective optimization model according to a multi-objective evolutionary algorithm to determine the incidence relation of the alarm data of the different types of vehicles comprises:
and in the process of solving the multi-objective optimization model according to a multi-objective evolutionary algorithm, determining the incidence relation of the alarm data of the different types of vehicles by adopting alpha domination control domination weight.
6. The method of claim 1, wherein the correlation of different categories of vehicle warning data is a correlation of one category of vehicle warning data and another category of vehicle warning data.
7. The method of any one of claims 1-6, wherein the vehicle alarm data comprises at least two of state of charge alarm data, cell voltage alarm data, single probe temperature alarm data, battery pack voltage alarm data, drive motor temperature alarm data, drive motor speed alarm data, and motor controller temperature alarm data.
8. A vehicle alarm data knowledge map construction apparatus, the apparatus comprising: the system comprises an acquisition unit, an establishing unit, a solving unit and a display unit;
the acquisition unit is used for acquiring alarm data of various vehicles;
the establishing unit is used for establishing a multi-objective optimization model according to the combination of different types of vehicle alarm data in the multi-type vehicle alarm data;
the solving unit is used for solving the multi-objective optimization model according to a multi-objective evolutionary algorithm and determining the incidence relation of the alarm data of the vehicles of different types;
and the display unit is used for constructing a vehicle alarm data knowledge graph according to the incidence relation.
9. A vehicle alert data knowledge map construction apparatus, the apparatus comprising a processor and a memory:
the memory is used for storing a computer program and transmitting the computer program to the processor;
the processor is configured to execute the vehicle alert data knowledge graph construction method of any one of claims 1 to 7 in accordance with instructions in the computer program.
10. A computer-readable storage medium for storing a computer program for executing the vehicle alert data knowledge graph construction method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011640728.2A CN112699171A (en) | 2020-12-31 | 2020-12-31 | Vehicle alarm data knowledge graph construction method and related device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011640728.2A CN112699171A (en) | 2020-12-31 | 2020-12-31 | Vehicle alarm data knowledge graph construction method and related device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112699171A true CN112699171A (en) | 2021-04-23 |
Family
ID=75513961
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011640728.2A Pending CN112699171A (en) | 2020-12-31 | 2020-12-31 | Vehicle alarm data knowledge graph construction method and related device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112699171A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109460010A (en) * | 2018-12-18 | 2019-03-12 | 彩虹无线(北京)新技术有限公司 | The vehicle fault detection method, apparatus and storage medium of knowledge based map |
CN110647539A (en) * | 2019-09-26 | 2020-01-03 | 汉纳森(厦门)数据股份有限公司 | Prediction method and system for vehicle faults |
CN110727804A (en) * | 2019-10-11 | 2020-01-24 | 北京明略软件系统有限公司 | Method and device for processing maintenance case by using knowledge graph and electronic equipment |
CN111767440A (en) * | 2020-09-03 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Vehicle portrayal method based on knowledge graph, computer equipment and storage medium |
CN111832974A (en) * | 2020-07-28 | 2020-10-27 | 重庆长安新能源汽车科技有限公司 | Vehicle fault early warning method and storage medium |
CN111915207A (en) * | 2020-08-11 | 2020-11-10 | 中国民航科学技术研究院 | Civil aviation safety risk analysis method and device based on knowledge graph |
CN112000773A (en) * | 2020-08-25 | 2020-11-27 | 城云科技(中国)有限公司 | Data association relation mining method based on search engine technology and application |
CN112183771A (en) * | 2020-08-18 | 2021-01-05 | 北京城建信捷轨道交通工程咨询有限公司 | Intelligent operation and maintenance ecosystem for rail transit and operation method thereof |
-
2020
- 2020-12-31 CN CN202011640728.2A patent/CN112699171A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109460010A (en) * | 2018-12-18 | 2019-03-12 | 彩虹无线(北京)新技术有限公司 | The vehicle fault detection method, apparatus and storage medium of knowledge based map |
CN110647539A (en) * | 2019-09-26 | 2020-01-03 | 汉纳森(厦门)数据股份有限公司 | Prediction method and system for vehicle faults |
CN110727804A (en) * | 2019-10-11 | 2020-01-24 | 北京明略软件系统有限公司 | Method and device for processing maintenance case by using knowledge graph and electronic equipment |
CN111832974A (en) * | 2020-07-28 | 2020-10-27 | 重庆长安新能源汽车科技有限公司 | Vehicle fault early warning method and storage medium |
CN111915207A (en) * | 2020-08-11 | 2020-11-10 | 中国民航科学技术研究院 | Civil aviation safety risk analysis method and device based on knowledge graph |
CN112183771A (en) * | 2020-08-18 | 2021-01-05 | 北京城建信捷轨道交通工程咨询有限公司 | Intelligent operation and maintenance ecosystem for rail transit and operation method thereof |
CN112000773A (en) * | 2020-08-25 | 2020-11-27 | 城云科技(中国)有限公司 | Data association relation mining method based on search engine technology and application |
CN111767440A (en) * | 2020-09-03 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Vehicle portrayal method based on knowledge graph, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111241154B (en) | Storage battery fault early warning method and system based on big data | |
CN112092675B (en) | Battery thermal runaway early warning method, system and server | |
CN108445410B (en) | Method and device for monitoring running state of storage battery pack | |
US8855954B1 (en) | System and method for prognosticating capacity life and cycle life of a battery asset | |
CN111208445A (en) | Power battery abnormal monomer identification method and system | |
CN106054858B (en) | The method of the vehicle remote diagnosis and spare part retrieval classified based on decision tree classification and error code | |
EP4198531A1 (en) | Battery cell defectiveness and fire early diagnosis method and apparatus based on neural network | |
CN109947898B (en) | Equipment fault testing method based on intellectualization | |
CN113760670A (en) | Cable joint abnormity early warning method and device, electronic equipment and storage medium | |
CN109636047A (en) | User activity prediction model training method, system, equipment and storage medium | |
CN103443809A (en) | Discriminant model learning device, method and program | |
CN115372828A (en) | Battery cell consistency evaluation method based on charging segment data and unsupervised algorithm | |
CN115330275B (en) | Echelon utilization method and device for retired battery | |
CN111339072B (en) | User behavior-based change value analysis method and device, electronic equipment and medium | |
CN112816885A (en) | Battery abnormity detection method and device, electronic equipment and storage medium | |
Aikhuele | Development of a fixable model for the reliability and safety evaluation of the components of a commercial lithium-ion battery | |
CN110009062B (en) | Classification model training method and device | |
CN112699171A (en) | Vehicle alarm data knowledge graph construction method and related device | |
CN112070180B (en) | Power grid equipment state judging method and device based on information physical bilateral data | |
CN114036647A (en) | Power battery safety risk assessment method based on real vehicle data | |
CN111949646B (en) | Equipment running condition analysis method, device, equipment and medium based on big data | |
CN113256325A (en) | Second-hand vehicle valuation method, system, computing device and storage medium | |
CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
CN117310500A (en) | Battery state classification model construction method and battery state classification method | |
CN115700363B (en) | Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium |
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 |