CN109596913A - Charging pile failure cause diagnostic method and device - Google Patents
Charging pile failure cause diagnostic method and device Download PDFInfo
- Publication number
- CN109596913A CN109596913A CN201811416032.4A CN201811416032A CN109596913A CN 109596913 A CN109596913 A CN 109596913A CN 201811416032 A CN201811416032 A CN 201811416032A CN 109596913 A CN109596913 A CN 109596913A
- Authority
- CN
- China
- Prior art keywords
- charging pile
- data
- fault
- bayesian network
- failure cause
- 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.)
- Granted
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
It includes: the fault type that the target charging pile is obtained when target charging pile breaks down that the application, which provides a kind of charging pile failure cause diagnostic method and device, method,；Preset Bayesian network model, and the corresponding failure cause diagnostic result of fault type by the output of the Bayesian network model as the target charging pile are inputted using the fault type of the target charging pile as forecast sample；Wherein, the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table, and the topological structure of the Bayesian network is used to indicate corresponding relationship between each fault type of charging pile and each failure cause diagnostic result.The failure cause that the application can be realized charging pile diagnoses automatically, and diagnose processing efficient and diagnostic result it is accurate, and then can to quickly confirm when charging pile breaks down the failure occur the reason of, and then can in time and targetedly charging pile is repaired.
Description
Technical field
This application involves charging pile equipment technical fields, and in particular to a kind of charging pile failure cause diagnostic method and dress
It sets.
Background technique
With science and technology rapid development and the increasingly raising of people's environmental consciousness, more and more electrically driven vehicles are by people
Favor.And the important corollary equipment as electrically driven vehicle, charging pile also come into being.With more and more chargings
How stake investment application, confirm that its failure cause to carry out on-call maintenance to it, also becomes guarantor when charging pile breaks down
Demonstrate,prove the important research method in the running quality project of charging pile.
In the prior art, the failure cause diagnostic mode of charging pile generallys use the mode of artificial plan repair charging pile
It realizes, if find failure during inspection, the investigation of failure cause is carried out for the failure, and finally confirm the failure
Occurrence cause.
However, since the failure cause diagnostic mode of existing charging pile is to determine generation by artificial plan repair
The reason of failure, such mode can only confirm after artificial maintenance investigation failure cause, so that for charging pile
Failure cause diagnoses process passively and inefficiency, in addition, being easy to lead since artificial planned tour strategy lacks customization foundation
The phenomenon that causing excessively maintenance and lacking maintenance, generates the wasting of resources and mispairing.
Summary of the invention
For the problems of the prior art, the application provides a kind of charging pile failure cause diagnostic method and device, can
It realizes that the failure cause of charging pile diagnoses automatically, and diagnoses processing efficient and diagnostic result is accurate, and then it can be in charging pile
Quickly confirm when breaking down the failure occur the reason of, and then can in time and targetedly charging pile is repaired.
In order to solve the above technical problems, the application the following technical schemes are provided:
In a first aspect, the application provides a kind of charging pile failure cause diagnostic method, comprising:
The fault type of the target charging pile is obtained when target charging pile breaks down；
Preset Bayesian network model is inputted using the fault type of the target charging pile as forecast sample, and should
Fault type corresponding failure cause diagnostic result of the output of Bayesian network model as the target charging pile；
Wherein, the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table,
And the topological structure of the Bayesian network is used to indicate each fault type and each failure cause diagnostic result of charging pile
Between corresponding relationship.
Further, further includes:
According to the various faults type of charging pile and its corresponding known fault cause diagnosis as a result, generating training sample
Collection；
Using the training sample set, the topology knot of Bayesian network is established based on corresponding score function and searching algorithm
Structure；
Determine that the condition at each node in the topological structure of the Bayesian network is general based on Maximum Likelihood Estimation
Rate obtains the conditional probability table of each node.
Further, various faults type and its corresponding known fault cause diagnosis according to charging pile as a result,
Generate training sample set, comprising:
An at least number from the telemetry, remote signalling data power module monitoring data and transaction data of electric system
According to the middle history data for extracting multiple charging piles；
The corresponding charging pile fault signature data of various faults type of charging pile are extracted in the history data,
And charging pile failure is established according to the subordinate relation between the corresponding charging pile fault signature data of various fault types and is referred to
Mark system；
The corresponding charging pile fault signature data of the charging pile fault indices body are pre-processed；
Training sample set is generated according to charging pile fault signature data after pretreatment.
Further, described that the corresponding charging pile fault signature data of the charging pile fault indices system are located in advance
Reason, comprising:
Data cleansing and/or attribute are carried out to the corresponding charging pile fault signature data of the charging pile fault indices system
Specification processing；
Data transformation will be carried out through data cleansing and/or attitude layer treated charging pile fault signature data.
Second aspect, the application provide a kind of charging pile failure cause diagnostic device, comprising:
The fault type of target charging pile obtains module, for obtaining target charging when target charging pile breaks down
The fault type of stake；
Target faults cause diagnosis module, it is pre- for being inputted using the fault type of the target charging pile as forecast sample
If Bayesian network model, and by the Bayesian network model output as the target charging pile fault type it is corresponding
Failure cause diagnostic result；
Wherein, the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table,
And the topological structure of the Bayesian network is used to indicate each fault type and each failure cause diagnostic result of charging pile
Between corresponding relationship.
Further, further includes:
Training sample set generation module, for the various faults type and its corresponding known fault reason according to charging pile
Diagnostic result generates training sample set；
Bayesian Network Topology Structures establish module, for applying the training sample set, are based on corresponding score function
And searching algorithm establishes the topological structure of Bayesian network；
Conditional probability obtains module, for determining the topological structure of the Bayesian network based on Maximum Likelihood Estimation
In each node at conditional probability, obtain the conditional probability table of each node.
Further, the training sample set generation module includes:
History data acquiring unit monitors number for the telemetry from electric system, remote signalling data power module
According to history data that multiple charging piles are extracted at least a data in transaction data；
Charging pile fault indices Establishing unit, for extracting a variety of events of charging pile in the history data
Hinder the corresponding charging pile fault signature data of type, and according to the corresponding charging pile fault signature data of various fault types
Between subordinate relation establish charging pile fault indices system；
Data pre-processing unit, for being carried out to the corresponding charging pile fault signature data of the charging pile fault indices body
Pretreatment；
Training sample set generation unit, for generating training sample according to charging pile fault signature data after pretreatment
Collection.
Further, the data pre-processing unit is specifically used for:
Data cleansing and/or attribute are carried out to the corresponding charging pile fault signature data of the charging pile fault indices system
Specification processing；
Data transformation will be carried out through data cleansing and/or attitude layer treated charging pile fault signature data.
The third aspect, the application provides a kind of electronic equipment, including memory, processor and storage are on a memory and can
The computer program run on a processor, the processor realize the charging pile failure cause diagnosis when executing described program
The step of method.
Fourth aspect, the application provide a kind of computer readable storage medium, are stored thereon with computer program, the calculating
The step of charging pile failure cause diagnostic method is realized when machine program is executed by processor.
As shown from the above technical solution, the application provides a kind of charging pile failure cause diagnostic method, by by the mesh
The fault type of charging pile is marked as the preset Bayesian network model of forecast sample input, and by the Bayesian network model
Export the corresponding failure cause diagnostic result of fault type as the target charging pile, wherein the Bayesian network model
Include Bayesian network topological structure and corresponding conditional probability table, and the topological structure of the Bayesian network be used for table
Show the corresponding relationship between each fault type of charging pile and each failure cause diagnostic result, can be realized the event of charging pile
Barrier reason diagnoses automatically, and diagnoses processing efficient and diagnostic result is accurate, and then can be to quick when charging pile breaks down
Confirm the reason of failure occurs, and then can in time and targetedly charging pile be repaired, and fortune can be effectively improved
Person works' efficiency is tieed up, and mitigates the maintenance work pressure for being directed to charging pile, meanwhile, it is simple that charging pile failure cause diagnoses process
And have scientific basis, effective data supporting can be provided for the daily maintenance work of charging pile, have it is very strong science,
Reliability and operability can effectively instruct the intelligent O&M of charging pile, promote electrically-charging equipment asset management and operation
Service work lean is horizontal, improves the operation stability and service life of electrically-charging equipment, shortens troubleshooting duration, improves money
It produces utilization rate and charging service is horizontal.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the application
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the flow diagram of the charging pile failure cause diagnostic method in the embodiment of the present invention.
Fig. 2 is the server S 1 in the embodiment of the present invention and the framework schematic diagram between client device B1.
Fig. 3 is the framework between server S 1, client device B1 and fault monitoring device B2 in the embodiment of the present invention
Schematic diagram.
Fig. 4 be the embodiment of the present invention in include charging pile failure cause diagnostic method of the step 001 to step 003
Flow diagram.
Fig. 5 be the embodiment of the present invention in charging pile failure cause diagnostic method in step 001 flow diagram.
Fig. 6 be the embodiment of the present invention in charging pile failure cause diagnostic method in step 001c flow diagram.
Fig. 7 is the structure example schematic diagram of the charging pile fault indices system in the embodiment of the present invention.
Fig. 8 is the structure example schematic diagram of the topological structure of the Bayesian network in the embodiment of the present invention.
Fig. 9 is the structural schematic diagram of the charging pile failure cause diagnostic device in the embodiment of the present invention.
Figure 10 be the embodiment of the present invention in include model building module 00 charging pile failure cause diagnostic device
Structural schematic diagram.
Figure 11 is training sample set generation module 01 in the charging pile failure cause diagnostic method in the embodiment of the present invention
Structural schematic diagram.
Figure 12 is the structural schematic diagram of the electronic equipment in the embodiment of the present invention.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, technical solutions in the embodiments of the present application carries out clear, complete description, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall in the protection scope of this application.
It is diversified due to constituting charging pile fault type, it is contemplated that the prior art often focuses on individually
To determine charging pile which kind of failure occurs for the threshold range of index, and the existing failure cause diagnosis for charging pile it is passive and
Inefficiency, and there are problems that excessively overhauling and lacking overhauling and generating the wasting of resources and mispairing, the application provides one kind and fills
Electric stake failure cause diagnostic method, charging pile failure cause diagnostic device, for realizing charging pile failure cause diagnosis side
The electronic equipment and computer storage medium of method.Wherein, charging pile failure cause diagnostic method is by by the target charging pile
Fault type input preset Bayesian network model as forecast sample, and using the output of the Bayesian network model as
The corresponding failure cause diagnostic result of the fault type of the target charging pile, wherein the Bayesian network model includes shellfish
The topological structure of this network of leaf and corresponding conditional probability table, and the topological structure of the Bayesian network is for indicating charging pile
Each fault type and each failure cause diagnostic result between corresponding relationship, can be realized the failure cause of charging pile from
Dynamic diagnosis, and diagnose processing efficient and diagnostic result is accurate, and then can be to quickly confirming the event when charging pile breaks down
The reason of barrier occurs, and then can in time and targetedly charging pile be repaired, and operation maintenance personnel work can be effectively improved
Make efficiency, and mitigates the maintenance work pressure for being directed to charging pile, meanwhile, charging pile failure cause diagnoses process simply and has section
Learn foundation, effective data supporting can be provided for the daily maintenance work of charging pile, have it is very strong science, reliability and
Operability can effectively instruct the intelligent O&M of charging pile, promote electrically-charging equipment asset management and operating maintenance work
Lean is horizontal, improves the operation stability and service life of electrically-charging equipment, shortens troubleshooting duration, improves asset utilization ratio
With charging service level.
In a kind of model training scene, the application also provides a kind of charging pile failure cause diagnostic device, which can
Think a kind of server S 1, referring to fig. 2, which can communicate to connect at least one client device B1, the visitor
The history data of multiple charging piles can be sent to the server S 1 online by family end equipment B1, and the server S 1 can
To receive the history data of the multiple charging pile online.The server S 1 can be online or offline in the history
The corresponding charging pile fault signature data of various faults type of charging pile are extracted in operation data, and according to various fault types
Subordinate relation between corresponding charging pile fault signature data establishes charging pile fault indices system, to the charging pile
The corresponding charging pile fault signature data of fault indices body are pre-processed, then special according to charging pile failure after pretreatment
Sign data generate training sample set and establish pattra leaves based on corresponding score function and searching algorithm using the training sample set
The topological structure of this network is determined based on Maximum Likelihood Estimation at each node in the topological structure of the Bayesian network
Conditional probability, obtain the conditional probability table of each node, and then complete the foundation of Bayesian network model.
Based on foregoing description, the server S 1 also could alternatively be the data for being accessed by the server S 1
Library, that is, the server S 1 can obtain the history data of charging pile with timesharing or timing from the database.
In a kind of model prediction scene, referring to Fig. 3, the server S 1 can also be at least one fault monitoring device
B2 communication connection, the fault monitoring device B2 can be the sensor or sensor being arranged on charging pile or line related
Group, such as voltage sensor, temperature sensor, humidity sensor and current sensor etc. are supervised in the fault monitoring device B2
When having measured charging pile and breaking down, the fault message is sent to the server S 1 online, the server S 1 connects online
It receives the fault message and is extracted online or offline from the fault message and obtain fault type, thereafter, the server S 1 is by institute
The fault type of target charging pile is stated as forecast sample and inputs preset Bayesian network model, and by the Bayesian network mould
Fault type corresponding failure cause diagnostic result of the output of type as the target charging pile, wherein the Bayesian network
Model include Bayesian network topological structure and corresponding conditional probability table, and the Bayesian network topological structure use
Corresponding relationship between each fault type and each failure cause diagnostic result for indicating charging pile, then, the service
The failure cause diagnostic result is sent to the client device B1 by device S1 online, so that the client device B1 is timely
The failure cause diagnostic result of charging pile failure is known, so that service personnel quickly and is directed to by client device B1
The corresponding charging pile failure of reparation of property.
Based on above content, the client device B1 can have display interface, allow users to be looked into according to interface
See the corresponding failure cause diagnostic result of charging pile failure for the target charging pile that the server S 1 is sent.
It is understood that the client device B1 may include smart phone, Flat electronic equipment, network machine top
Box, portable computer, desktop computer, personal digital assistant (PDA), mobile unit, intelligent wearable device etc..Wherein, described
Intelligent wearable device may include smart glasses, smart watches, Intelligent bracelet etc..
In practical applications, the part for carrying out the diagnosis of charging pile failure cause can be in the server as described in above content
The side S1 executes, that is, and framework as shown in Figure 2 or Figure 3, operation that can also be all are all completed in the client device B1,
And the client device B1 can be directly communicatively coupled with fault monitoring device B2 and electric system.It specifically can root
It is selected according to the processing capacity of the client device B1 and limitation of user's usage scenario etc..The application does not make this
It limits.If all operations are all completed in the client device B1, the client device B1 can also include processor,
For carrying out the specific processing of charging pile failure cause diagnosis.
Above-mentioned client device can have communication module (i.e. communication unit), can be with fault monitoring device and electric power
The long-range server of system is communicatively coupled, and realizes the long-range server with the fault monitoring device and electric system
Data transmission.For example, communication unit obtained by the long-range server of the electric system electric system telemetry,
Remote signalling data and power module monitoring data, so that client device constructs according to these related datas the pattra leaves of the charging pile
This network model.The server may include the server of task schedule center side, can also be in other implement scenes
Server including halfpace, such as have with task schedule central server the clothes of the third-party server platform of communication linkage
Business device.The server may include single computer unit, also may include the server cluster of multiple server compositions,
Or the server architecture of distributed devices.
Any suitable network protocol can be used between the server and the client device to be communicated, including
In the network protocol that the application submitting day is not yet developed.The network protocol for example may include ICP/IP protocol, UDP/IP
Agreement, http protocol, HTTPS agreement etc..Certainly, the network protocol for example can also include using on above-mentioned agreement
RPC agreement (Remote Procedure Call Protocol, remote procedure call protocol), REST agreement
(Representational State Transfer, declarative state transfer protocol) etc..
In one or more embodiments of the application, charging pile can be fixed on ground or wall, be installed on public build
It builds in (public building, market, Public Parking etc.) and residential area parking lot or charging station, it can be according to different voltage etc.
Grade is that the electric car of various models charges.The input terminal of charging pile is directly connected to AC network, and output end is equipped with charging
Plug is used to charge for electrically driven vehicle.Wherein, the electrically driven vehicle can be electric car, or pass through electricity
The other types vehicle of power drive.
The failure cause that the application can be realized charging pile diagnoses automatically, and diagnose processing efficient and diagnostic result it is accurate,
And then can be to failure generation is quickly confirmed when charging pile breaks down the reason of, and then can be in time and targetedly right
Charging pile repairs, and can effectively improve operation maintenance personnel working efficiency, and mitigates the maintenance work pressure for being directed to charging pile,
Meanwhile charging pile failure cause diagnosis process is simple and has scientific basis, can provide for the daily maintenance work of charging pile
Effective data supporting has very strong scientific, reliability and operability, can effectively instruct the intelligence of charging pile
O&M, promotes electrically-charging equipment asset management and operating maintenance work lean is horizontal, improve electrically-charging equipment operation stability and
Service life shortens troubleshooting duration, improves asset utilization ratio and charging service is horizontal.Especially by following embodiments and two
A application scenarios are specifically described.
In order to realize that the failure cause of charging pile diagnoses automatically, and make diagnosis process highly efficient and diagnostic result
Accurately, the embodiment of the present application provides a kind of charging pile failure cause diagnostic method, and referring to Fig. 1, the charging pile failure cause is examined
Disconnected method specifically includes following content:
Step 100: the fault type of the target charging pile is obtained when target charging pile breaks down；
Step 200: inputting preset Bayesian network mould for the fault type of the target charging pile as forecast sample
Type, and the corresponding failure cause diagnosis knot of fault type by the output of the Bayesian network model as the target charging pile
Fruit, wherein the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table, and it is described
The topological structure of Bayesian network is for indicating between each fault type of charging pile and each failure cause diagnostic result
Corresponding relationship.
It is understood that Bayesian network BN (Bayesian network model), also known as Belief Network, by one
Directed acyclic graph (Directed Acylic Graph, DAG) and conditional probability table (Conditional Probability
Table, CPT) composition.In Bayesian network, if two variable Xs and Y are connected directly, then it represents that have between them directly according to
The relationship of relying, will affect the reliability about Y to the understanding of X, vice versa.Under this meaning, we claim information can be at two
It is transmitted between the node being connected directly.On the other hand, if two variable Xs and Y are not connected directly, information needs to pass through it
Its variable could transmit therebetween.If all information channels between X and Y are all blocked, information just can not be
It is transmitted between them.At this moment, the reliability to another variable will not influence to the understanding of one of variable, thus X and Y are mutual
Conditional sampling.If it is considered that two variable Xs and Y are indirectly connected this basic condition by third variable Z, then it can be by Bayes
Network decomposition is at three kinds of basic structures, i.e., suitable to connect, company and remittance is divided to connect.
Wherein, it is mainly reflected in the advantages of Bayesian network:
(1) Bayesian network describes the correlation between data using the method for figure, semantic clear, should be readily appreciated that.Figure
The knowledge representation method of shape makes that the consistency in probabilistic knowledge library and integrality is kept to become easy, and is directed to item with can be convenient
The change of part carries out reconfiguring for network module.
(2) Bayesian network is easily handled Incomplete data set.It is necessary for the supervised learning algorithm of traditional standard
All possible data input is known, if deviation, Bayes will be generated to the model of foundation by lacking a certain input therein
What the method for network reflected is the updated by probability in entire database between data, and lacking a certain data variable still can build
Found accurate model.
(3) Bayesian network allows the causality between Variable Learning.In previous data analysis, problem because
For fruit relationship when interfering more, system can not just make accurate prediction.And oneself is included in Bayesian network for this causality
In network model.Bayes method have cause and effect and probability semanteme, can be used to learning data in causality, and according to because
Fruit relationship is learnt.
(4) Bayesian network combines the information that can make full use of domain knowledge and sample data with Bayesian statistics.
Bayesian network with arc indicate variable between dependence, the power of dependence is indicated with probability distribution table, priori is believed
Breath combines with sample knowledge, promotes integrating for priori knowledge and data, this sample data is sparse or data compared with
It is especially effective when unobtainable.
As can be seen from the above description, charging pile failure cause diagnostic method provided by the present application, by the way that the target is charged
The fault type of stake inputs preset Bayesian network model as forecast sample, and the output of the Bayesian network model is made
For the corresponding failure cause diagnostic result of fault type of the target charging pile, wherein the Bayesian network model includes
The topological structure of Bayesian network and corresponding conditional probability table, and the topological structure of the Bayesian network is for indicating charging
Corresponding relationship between each fault type and each failure cause diagnostic result of stake, can be realized the failure cause of charging pile
Automatic diagnosis, and diagnose processing efficient and diagnostic result is accurate, and then can be to quickly confirmation should when charging pile breaks down
The reason of failure occurs, and then can in time and targetedly charging pile be repaired, and operation maintenance personnel can be effectively improved
Working efficiency, and mitigate the maintenance work pressure for being directed to charging pile, meanwhile, charging pile failure cause diagnosis process is simple and has
Scientific basis can provide effective data supporting for the daily maintenance work of charging pile, have very strong scientific, reliability
And operability, the intelligent O&M of charging pile can be effectively instructed, electrically-charging equipment asset management and operating maintenance work are promoted
Make lean level, improve the operation stability and service life of electrically-charging equipment, shorten troubleshooting duration, improves assets utilization
Rate and charging service are horizontal.
In order to provide more accurate and targeted Bayesian network model, to further increase diagnosis process
The accuracy of efficiency and diagnostic result, in the embodiment of the application, the charging pile failure cause diagnostic method of the application is also
Include model foundation step, referring to fig. 4, the model foundation step specifically includes following content:
Step 001: according to the various faults type of charging pile and its corresponding known fault cause diagnosis as a result, generating instruction
Practice sample set.
Step 002: applying the training sample set, Bayesian network is established based on corresponding score function and searching algorithm
Topological structure.
Step 003: being determined based on Maximum Likelihood Estimation at each node in the topological structure of the Bayesian network
Conditional probability, obtain the conditional probability table of each node.
In order to the accuracy and reliability of further electric stake failure cause diagnosis, in the embodiment of the application also
The specific implementation of step 001 in charging pile failure cause diagnostic method is provided, referring to Fig. 5, the step 001 is specifically included
Following content:
Step 001a: from the telemetry, remote signalling data power module monitoring data and transaction data of electric system
The history data of multiple charging piles is extracted at least a data.
It is understood that the history data of the charging pile can be the history run number in default run the period
According to.For example, which can be 1 month, 3 months or 1 year etc..
Step 001b: the corresponding charging pile failure of various faults type of charging pile is extracted in the history data
Characteristic, and charging is established according to the subordinate relation between the corresponding charging pile fault signature data of various fault types
Stake fault indices system.
In a kind of concrete example, the malfunction of the charging pile at least be can wrap containing: smog alarm failure, exchange
Circuit breaker failure, DC bus fuse output failure, charger fan failure, surge arrester failure, scram button action failure,
Cabinet door abnormal opening failure, DC bus output contactor failure, electric discharge contactor failure, discharge resistance failure, electronic lock event
Barrier, insulating monitoring failure, battery reversal connection failure, do not playback failure, charging pile of control guiding failure, charging gun crosses reviewing knowledge already acquired in charging
Barrier, charging gun excess temperature failure, BMS communication abnormality, input voltage over-voltage fault, input voltage under-voltage fault, output voltage over-voltage
Failure, output voltage under-voltage fault, output overcurrent failure, output short-circuit failure, TCU communication abnormality, charging module communication alarm,
Charging module exchange input alarm, charging module exchange input over-voltage alarm, the alarm of charging module exchange input undervoltage, charging mould
Block exchanges input phase failure alarm, charging module direct current output short trouble, charging module direct current output over current fault, charging module
Direct current output over-voltage fault, charging module direct current output under-voltage fault, charging module excess temperature failure and charging module fan failure.
Step 001c: the corresponding charging pile fault signature data of the charging pile fault indices body are pre-processed.
Step 001d: training sample set is generated according to charging pile fault signature data after pretreatment.
In order to the accuracy and reliability that further Bayesian network model is established, in the embodiment of the application
The specific implementation of step 001c in charging pile failure cause diagnostic method is also provided, referring to Fig. 6, the step 001c is specific
Including following content:
Step 001c-1: it is clear that data are carried out to the corresponding charging pile fault signature data of the charging pile fault indices system
It washes and/or attitude layer is handled.
Step 001c-2: will treated that charging pile fault signature data count through data cleansing and/or attitude layer
According to transformation.
Based on above content, the charging pile failure cause diagnostic method of the application is passed through into following offline model construction fields
Scape and online model prediction scene are described in detail, and particular content is as follows:
(1) model training scene
S1- characteristic obtains:
The corresponding charging pile fault signature data of various faults type of charging pile are obtained, and according to various charging pile failures
Subordinate relation between characteristic establishes charging pile fault indices system.It is understood that described establish charging pile failure
Index system is specifically as follows the feature that the different faults type of charging pile is selectively extracted from preset operation system
Data, and charging pile fault indices system is established according to the subordinate relation between various fault types.
It is understood that the data source of the charging pile fault signature data, which includes at least, to be had: telemetry, remote signalling
Data, module data and transaction data etc..A kind of citing of the charging pile fault indices system is referring to Fig. 7 and the following table 1:
Table 1
Based on above-mentioned table 1, the charging pile fault indices system at least be can wrap containing 4 first class index, specifically: shape
State data A0, electric information data B0, switching value data C0 and environmental classes data D0 etc..
Wherein, status data A0 also includes two-level index, is specifically as follows: operating status A1, whether connect vehicle A2,
Direct current output contactor state A3 and charging interface electronics lock status A4 etc.；Electric information data B0 also includes two-level index, tool
Body can be with are as follows: input current B1, input voltage B2, output electric current B3, output voltage B4, state of insulation B5, voltage rating B6, volume
Constant current B7 etc.；On-off state data C0 also includes two-level index, is specifically as follows: emergency stop C1, gate C2, output contact
Device C3, electric discharge contactor C4, auxiliary contactor C5 and electronic lock feedback point C6 etc.；Environmental classes data D0 also includes that second level refers to
Mark, is specifically as follows: charging module temperature D1, charging gun temperature D2, charger internal temperature D3 and charger interior humidity D4
Deng.
S2- data prediction:
The charging pile fault signature data are pre-processed.It is understood that the pretreated mode is at least
It can wrap containing modes such as data cleansing, attitude layer and data transformation.It is understood that data cleansing mode therein is extremely
It can wrap less and contain the processing means such as outlier identification, missing values interpolation and data deduplication.Specifically:
(1) data cleansing:
Outlier identification is carried out to the charging pile fault signature data, and the exceptional value that will identify that is from the charging pile
It is deleted in fault signature data, and, missing identification is carried out to the charging pile fault signature data, and missing values are incorporated into
Corresponding position in the charging pile fault signature data, in addition, repeated data identification is carried out to the charging pile fault signature,
And the repeated data that will identify that is deleted from the charging pile fault signature data.
(2) attitude layer:
Calculate the corresponding comentropy of various fault types in the charging pile fault signature data, and from the charging
Data corresponding to the fault type attribute that comentropy is 0 are deleted in stake fault signature data.Wherein, the mesh of the attitude layer
Be to search out the smallest attribute set, and ensure the probability distribution of new data subset close to the general of original data set
Rate distribution.
For example, if be computed know in above-mentioned table 1 whether connection vehicle A2, direct current output contactor state A3, charging
The comentropy of interface electronics lock status A4, emergency stop C1 and output contactor C3 are 0, then from the charging pile fault signature data
Data corresponding to these fault types are deleted.
(3) data convert:
Data transformation is carried out to through above-mentioned data cleansing and attitude layer treated charging pile fault signature data, specifically
Numeralization processing can be carried out using the mode of sliding-model control or the mode of application one-hot coding One-Hot-Encoder.
The one-hot coding method is to be encoded using N bit status register to N number of state, and each state has it independent to post
Storage position, and when any, wherein only one is effective.
For example, can be to operating status A1, the input voltage in the charging pile fault signature data as shown in Table 1
B2, input current B1, output voltage B4, output electric current B3, state of insulation B5, voltage rating B6, rated current B7 institute are right respectively
The data answered carry out sliding-model control, and to the output overvoltage in the charging pile fault signature data, output overcurrent, insulation event
The corresponding fault types such as barrier, module alerts, charger communication abnormality, the excessively high data of battery pack temperature are carried out using one-hot coding
Numeralization processing.
S3- training sample set generates:
It is used for according to through data cleansing, attitude layer and the transformed charging pile fault signature data of data, generation
The training sample set of the training Bayesian network.
S4- Bayesian Network Topology Structures are established:
The study that Bayesian Network Topology Structures are carried out based on the algorithm of scoring and search, is found and sample data sets
With spending best bayesian network structure, that is to say, that the target of Bayesian Network Topology Structures study is to find and sample number
According to the best bayesian network structure of sets match degree.The study of bayesian network structure includes the calculation based on scoring and search
Method, algorithm and hybrid algorithm based on constraint.Wherein, the algorithm based on scoring and search uses some standards of grading, judges net
The matching degree of independence and dependence and data that network structure reflects, a certain searching algorithm search score value of reselection are highest
Network model.The algorithmic procedure is simple, standardizes, and can reach global optimum by TABU search, therefore the algorithm is selected to carry out shellfish
The study of this network topology structure of leaf.
It is respectively the selection and search of score function that the foundation of bayesian network structure, which needs two main problems solved,
The selection of method, specific as follows:
(1) score function is determined:
The corresponding score function of Bayesian network is determined according to training sample set.
Common score function is based on information theory criterion, and problem concerning study is equivalent to a data compression and appointed by such criterion
Business, the target of study is to find the model that training data can be described with most short code length, and the length encoded at this time includes
Byte length needed for descriptive model itself and byte length needed for using the model describing data.To Bayesian network
For habit, model is exactly a Bayesian network, meanwhile, each Bayesian network describes a probability on the training data
Distribution, the sample that having a set of encoding mechanism by oneself can be such that those often occur has shorter.Therefore, that synthesis coding length should be selected
Degree (including description network and coded data) shortest Bayesian network, above-mentioned is minimum description length (Minimal
Description Length, abbreviation MDL) criterion.
Given training set D={ x1,x2...,xm, Bayesian network B=<G, θ>score function on D are writeable are as follows:
S (B | D)=f (θ) | B |-LL (B | D) (1)
In formula (1), | B | it is the number of parameters of Bayesian network；F (θ) indicates byte number needed for describing each parameter θ；
It is thereinIt is the log-likelihood of Bayesian network B.Obviously, the first item f (θ) of formula (1) | B |
It is byte number needed for calculation code Bayesian network, and Section 2 LL (B | D) it is to calculate probability distribution P corresponding to BBIt need to be how much
Byte describes D.Then, learning tasks translate into an optimization task, that is, finding a Bayesian network B makes score function
S (B | D) it is minimum.
If f (θ)=1, i.e., each parameter is described with 1 byte, then obtains akaike information criterion AIC (Akaike
Information criterion) score function AIC (B | D) are as follows:
AIC (B | D)=| B |-LL (B | D)
IfI.e. each parameter is usedA byte description, then obtain Bayesian Information rule BIC
(Bayesian Information Criterions) score function BIC (B | D) are as follows:
Obviously, if f (θ)=0, i.e., do not calculate the length encoded to network, then score function degeneration is negative logarithm seemingly
So, correspondingly, it is Maximum-likelihood estimation that learning tasks, which are degenerated,.
(2) searching algorithm:
In the case where score function has been determined, the problem concerning study of Bayesian network has reformed into a search problem.It searches
Rope algorithm is to search for the highest bayesian network structure of score value under some score function.When variables number increases, search
Rope space will with the index rank of interstitial content increase, find optimal model be able to solve there are multinomial algorithm it is non-certainly
Qualitative question NP (Non-Deterministic Polynomial Problems).It is such as greedy at present frequently with heuristic search
Search, optimal searches for scheduling algorithm at simulated annealing at first.
Most common searching method is the continuous directed edge changed in network structure, judges the shadow changed every time to score value
It rings.If there are directed edges between two variables, changing direction can be deletion directed edge or reverses directed edge；If two
Directed edge is not present between a variable, then evolutionary mode can be the directed edge for increasing any direction, but when changing, cannot generate
Directed circuit.
Simplest searching algorithm is greedy search (Greedy Search).Network knot may be added to by enabling E indicate all
Candidate side collection in structure, Δ (e) indicate that the side e in E is added to the changing value of rear score function in network structure.So search is calculated
Method can be described as:
1) an initial network structure is selected；
2) selection is candidate in the while e concentrated, so that Δ (e) > Δ (e'), wherein and e' is any side in E in addition to e, and
Δ (e) > 0 stops if can not find the side of the condition of satisfaction, otherwise turns 3)；
3) plus e is into network structure, and the side is deleted from Candidate Set E, turns 2)；
In the algorithm, initial network structure can be abortive haul, Stochastic Networks or the priori net built using Heuristics.It is greedy
Search strategy is a kind of local searching strategy, there are problems that falling into local extremum and saddle point.A kind of method of solution is when falling into
When entering local extremum or saddle point, the random structure for changing network may jump out saddle point or jump from a local extremum region
To another extremal region.
(3) topological structure of Bayesian network is determined based on score function and searching algorithm:
Citing based on Bayesian Network Topology Structures (directed acyclic graph) DAG learnt with searching algorithm that scores is such as
Shown in Fig. 8, Bayesian Network Topology Structures are explained as shown in the pseudocode of table 2:
Table 2
The study of S5- Bayesian network parameters:
The study of Bayesian network parameters is carried out based on Maximum-likelihood estimation, i.e., in given Bayesian Network Topology Structures
In the case of, determine the conditional probability at each node.
The target of Bayesian network parameters study is given network topology structure G and training sample set D, is known using priori
Know, determines the conditional probability density at each node of Bayesian network model, be denoted as: p (θ | D, G).Common parametric learning method
There are maximum likelihood estimation algorithm and Bayesian Estimation algorithm etc..Maximum likelihood estimation algorithm is a large amount of suitable for data, the ginseng of estimation
Number can preferably reflect actual conditions.Therefore, in one embodiment of the application, select Maximum-likelihood estimation as pattra leaves
The study of this network parameter.
(1) Maximum-likelihood estimation:
During Maximum-likelihood estimation, when parameter is the value by calculating given father node collection, node difference value
The frequency of occurrences, and the conditional probability parameter using it as the node.The basic principle of maximal possibility estimation is exactly to attempt to look for making
Obtain the maximum parameter of likelihood function.Parameter when maximal possibility estimation seeks to that likelihood function is used to get maximum value is as estimation
Value, likelihood function can indicate are as follows:
Due to there is even multiplication, usually take the calculating of logarithm more easy likelihood function, i.e. log-likelihood function, maximum
Possibility predication problem can be write as:
This is a function about θ, solves this optimization problem usually to θ derivation, obtains the extreme point that derivative is 0.
When the function obtains maximum value, the corresponding value of θ is exactly that we estimate to obtain model parameter.
(2) the conditional probability table CPT of network node:
Under conditions of given network topology structure G and training sample set D, the net that learns with Maximum-likelihood estimation
The conditional probability table CPT of each node of network is as follows:
1) the conditional probability table CPT of input voltage is as shown in table 3:
Table 3
2) the conditional probability table CPT of input current is as shown in table 4:
Table 4
| [30.7,31] | (31,91] |
| 0.93430657 | 0.06569343 |
3) the conditional probability table CPT of output voltage is as shown in table 5 to 7:
Operating status=charging, referring to table 5:
Table 5
Operating status=standby, referring to table 6:
Table 6
Operating status=stopping charging, referring to table 7:
Table 7
4) the conditional probability table CPT for exporting electric current is as shown in table 8:
Table 8
5) the conditional probability table CPT of operating status is as shown in table 9:
Table 9
6) the conditional probability table CPT of state of insulation is as shown in table 10:
Table 10
7) the conditional probability table CPT of voltage rating is as shown in table 11:
Table 11
8) the conditional probability table CPT of rated current is as shown in table 12:
Table 12
9) the conditional probability table CPT of output overvoltage is as shown in table 13:
Table 13
10) the conditional probability table CPT of output overcurrent is as shown in table 14:
Table 14
11) the conditional probability table CPT of insulation fault is as shown in Table 15:
Table 15
12) the conditional probability table CPT of module alerts is as shown in table 16 and 17:
Charger communication abnormality=0, referring to table 16:
Table 16
Charger communication abnormality=1, referring to table 17:
Table 17
13) the conditional probability table CPT of charger communication abnormality is as shown in table 18:
Table 18
14) the conditional probability table CPT of the excessively high failure of battery pack temperature is as shown in table 19:
Table 19
(2) model prediction scene
S1: the fault type of the target charging pile is obtained when target charging pile breaks down.
S2: pre-processing the fault type data of the target charging pile, specifically includes data cleansing, attribute rule
The about processing modes such as processing and data transformation.
S3: preset Bayesian network model is inputted using pretreated fault type data as forecast sample, and will
Fault type corresponding failure cause diagnostic result of the output of the Bayesian network model as the target charging pile.Specific place
Reason mode is as follows:
Certain feature nodes are calculated when failure occurs according to the topological structure and its conditional probability table of Bayesian network
The probability of value, to obtain the diagnostic result of failure cause.
Bayesian Network Inference refers to the structure and its conditional probability table using Bayesian network, calculates after given evidence
The probability of certain node values.
Conditional inference parameter setting: event=" fault signature ", evidence=" fault type ", i.e., charging pile not
When occurring with fault type, the probability of each feature node value is derived, to obtain the result of failure cause diagnosis.
Under conditions of output overvoltage failure occurs, output voltage (652,684] probability in section is 0.5350123,
And pseudocode is as shown in table 20:
Table 20
Under conditions of output overcurrent failure occurs, output electric current (85.4,94.2] probability in section is
0.5899238, and pseudocode is as shown in table 21:
Table 21
Under conditions of battery pack temperature excessively high failure occurs, output voltage in [0,652] and output electric current [0,
85.4] probability is 0.5917889, and pseudocode is as shown in table 22:
Table 22
Under conditions of insulation fault occurs, the probability of state of insulation "abnormal" is 1, and pseudocode is as shown in table 23:
Table 23
Under conditions of module alerts occur, output electric current (85.4,94.2] probability in section is 1, and pseudocode is such as
Shown in table 24:
Table 24
Under conditions of charger communication abnormality occurs, output electric current [0,85.4], output voltage (652,684],
Operating status is that the probability of " charging " is 0.3509587, and pseudocode is as shown in Table 25:
Table 25
S4: the corresponding failure cause diagnostic result of fault type of the target charging pile is exported.
As can be seen from the above description, charging pile failure cause diagnostic method provided by the present application, can be realized the event of charging pile
Barrier reason diagnoses automatically, and diagnoses processing efficient and diagnostic result is accurate, and then can be to quick when charging pile breaks down
Confirm the failure occur the reason of, and then can in time and targetedly charging pile is repaired.
In order to realize that the failure cause of charging pile diagnoses automatically, and make diagnosis process highly efficient and diagnostic result
Accurately, the embodiment of the present application provides a kind of charging pile for realizing full content in the charging pile failure cause diagnostic method
The specific embodiment of failure cause diagnostic device, referring to Fig. 9, the charging pile failure cause diagnostic device is specifically included in following
Hold:
The fault type of target charging pile obtains module 10, fills for obtaining the target when target charging pile breaks down
The fault type of electric stake.
Target faults cause diagnosis module 20, for being inputted the fault type of the target charging pile as forecast sample
Preset Bayesian network model, and the output of the Bayesian network model is corresponding as the fault type of the target charging pile
Failure cause diagnostic result, wherein the Bayesian network model includes the topological structure of Bayesian network and corresponding
Conditional probability table, and the topological structure of the Bayesian network is used to indicate that each fault type of charging pile and each failure to be former
Because of the corresponding relationship between diagnostic result.
The embodiment of charging pile failure cause diagnostic device provided by the present application specifically can be used for executing above-described embodiment
In charging pile failure cause diagnostic method each embodiment whole process flows, details are not described herein for function, can be with
Referring to the detailed description of above method embodiment.
As can be seen from the above description, charging pile failure cause diagnostic device provided by the embodiments of the present application, is charged by target
The fault type of stake obtains module 10 and inputs preset Bayes for the fault type of the target charging pile as forecast sample
Network model, and by target faults cause diagnosis module 20 using the output of the Bayesian network model as the target charging pile
The corresponding failure cause diagnostic result of fault type, wherein the Bayesian network model includes opening up for Bayesian network
Structure and corresponding conditional probability table are flutterred, and the topological structure of the Bayesian network is used to indicate each failure classes of charging pile
Corresponding relationship between type and each failure cause diagnostic result, the failure cause that can be realized charging pile diagnoses automatically, and examines
Disconnected processing efficient and diagnostic result is accurate, and then can be to the original for quickly confirming that the failure occurs when charging pile breaks down
Cause, and then can in time and targetedly charging pile be repaired, and operation maintenance personnel working efficiency can be effectively improved, and subtract
The light maintenance work pressure for being directed to charging pile, meanwhile, charging pile failure cause diagnoses process simply and has scientific basis, can
Effective data supporting is provided for the daily maintenance work of charging pile, there is very strong scientific, reliability and operability, energy
Enough intelligent O&Ms for effectively instructing charging pile, promote electrically-charging equipment asset management and operating maintenance work lean is horizontal,
The operation stability and service life of electrically-charging equipment are improved, troubleshooting duration is shortened, improves asset utilization ratio and charging service
It is horizontal.
In order to provide more accurate and targeted Bayesian network model, to further increase diagnosis process
The accuracy of efficiency and diagnostic result, in the embodiment of the application, the charging pile failure cause diagnostic device of the application is also
Include model building module 00, referring to Figure 10, the model building module 00 specifically includes following content:
Training sample set generation module 01, for former according to the various faults type of charging pile and its corresponding known fault
Because of diagnostic result, training sample set is generated.
Bayesian Network Topology Structures establish module 02, for applying the training sample set, are based on corresponding scoring letter
Several and searching algorithm establishes the topological structure of Bayesian network.
Conditional probability obtains module 03, for determining that the topology of the Bayesian network is tied based on Maximum Likelihood Estimation
The conditional probability at each node in structure, obtains the conditional probability table of each node.
In order to the accuracy and reliability of further electric stake failure cause diagnosis, in the embodiment of the application also
The specific implementation of training sample set generation module 01 in charging pile failure cause diagnostic device is provided, it is described referring to Figure 11
Training sample set generation module 01 specifically includes following content:
History data acquiring unit 01a, for the telemetry from electric system, the monitoring of remote signalling data power module
The history data of multiple charging piles is extracted at least a data in data and transaction data.
Charging pile fault indices Establishing unit 01b, for extracting the more of charging pile in the history data
The corresponding charging pile fault signature data of kind fault type, and according to the corresponding charging pile fault signature of various fault types
Subordinate relation between data establishes charging pile fault indices system.
Data pre-processing unit 01c, for the corresponding charging pile fault signature data of the charging pile fault indices body
It is pre-processed.
Training sample set generation unit 01d is trained for being generated according to charging pile fault signature data after pretreatment
Sample set.
In order to the accuracy and reliability that further Bayesian network model is established, in the embodiment of the application
The specific implementation of data pre-processing unit 01c in charging pile failure cause diagnostic device, the data prediction are also provided
Unit 01c is specifically used for: carrying out data cleansing to the corresponding charging pile fault signature data of the charging pile fault indices system
And/or attitude layer processing；Data will be carried out through data cleansing and/or attitude layer treated charging pile fault signature data
Transformation.
As can be seen from the above description, charging pile failure cause diagnostic device provided by the present application, can be realized the event of charging pile
Barrier reason diagnoses automatically, and diagnoses processing efficient and diagnostic result is accurate, and then can be to quick when charging pile breaks down
Confirm the failure occur the reason of, and then can in time and targetedly charging pile is repaired.
Embodiments herein also provides complete in the charging pile failure cause diagnostic method that can be realized in above-described embodiment
The specific embodiment of a kind of electronic equipment of portion's step, referring to Figure 12, the electronic equipment specifically includes following content:
Processor (processor) 601, memory (memory) 602, communication interface (Communications
Interface) 603 and bus 604；
Wherein, the processor 601, memory 602, communication interface 603 complete mutual lead to by the bus 604
Letter；The communication interface 603 for realizing charging pile failure cause diagnostic device, client terminal, fault monitoring device and its
He participates in the transmission of the information between mechanism；
The processor 601 is used to call the computer program in the memory 602, and the processor executes the meter
The Overall Steps in the charging pile failure cause diagnostic method in above-described embodiment are realized when calculation machine program, for example, the processing
Device realizes following step when executing the computer program:
Step 100: the fault type of the target charging pile is obtained when target charging pile breaks down；
Step 200: inputting preset Bayesian network mould for the fault type of the target charging pile as forecast sample
Type, and the corresponding failure cause diagnosis knot of fault type by the output of the Bayesian network model as the target charging pile
Fruit, wherein the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table, and it is described
The topological structure of Bayesian network is for indicating between each fault type of charging pile and each failure cause diagnostic result
Corresponding relationship.
As can be seen from the above description, electronic equipment provided by the present application, by the way that the fault type of the target charging pile is made
Preset Bayesian network model is inputted for forecast sample, and using the output of the Bayesian network model as the target charging pile
The corresponding failure cause diagnostic result of fault type, wherein the Bayesian network model includes opening up for Bayesian network
Structure and corresponding conditional probability table are flutterred, and the topological structure of the Bayesian network is used to indicate each failure classes of charging pile
Corresponding relationship between type and each failure cause diagnostic result, the failure cause that can be realized charging pile diagnoses automatically, and examines
Disconnected processing efficient and diagnostic result is accurate, and then can be to the original for quickly confirming that the failure occurs when charging pile breaks down
Cause, and then can in time and targetedly charging pile be repaired, and operation maintenance personnel working efficiency can be effectively improved, and subtract
The light maintenance work pressure for being directed to charging pile, meanwhile, charging pile failure cause diagnoses process simply and has scientific basis, can
Effective data supporting is provided for the daily maintenance work of charging pile, there is very strong scientific, reliability and operability, energy
Enough intelligent O&Ms for effectively instructing charging pile, promote electrically-charging equipment asset management and operating maintenance work lean is horizontal,
The operation stability and service life of electrically-charging equipment are improved, troubleshooting duration is shortened, improves asset utilization ratio and charging service
It is horizontal.
Embodiments herein also provides complete in the charging pile failure cause diagnostic method that can be realized in above-described embodiment
A kind of computer readable storage medium of portion's step is stored with computer program on the computer readable storage medium, the meter
Calculation machine program realizes the Overall Steps of the charging pile failure cause diagnostic method in above-described embodiment, example when being executed by processor
Such as, following step is realized when the processor executes the computer program:
Step 100: the fault type of the target charging pile is obtained when target charging pile breaks down；
Step 200: inputting preset Bayesian network mould for the fault type of the target charging pile as forecast sample
Type, and the corresponding failure cause diagnosis knot of fault type by the output of the Bayesian network model as the target charging pile
Fruit, wherein the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table, and it is described
The topological structure of Bayesian network is for indicating between each fault type of charging pile and each failure cause diagnostic result
Corresponding relationship.
As can be seen from the above description, computer readable storage medium provided by the present application, the failure that can be realized charging pile is former
It because of automatic diagnosis, and diagnoses processing efficient and diagnostic result is accurate, and then can quickly confirm to when charging pile breaks down
The failure occur the reason of, and then can in time and targetedly charging pile is repaired.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for hardware+
For program class embodiment, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to side
The part of method embodiment illustrates.Although this specification embodiment provides the operation of the method as described in embodiment or flow chart
Step, but may include more or less operating procedure based on conventional or without creativeness means.It is enumerated in embodiment
The step of sequence be only one of numerous step execution sequence mode, do not represent and unique execute sequence.In practice
It, can be according to embodiment or the execution of method shown in the drawings sequence or parallel execution (example when device or end product execute
Such as parallel processor or the environment of multiple threads, even distributed data processing environment).The terms "include", "comprise"
Or any other variant thereof is intended to cover non-exclusive inclusion, so that including the process, method of a series of elements, producing
Product or equipment not only include those elements, but also including other elements that are not explicitly listed, or further include for this
Kind of process, method, product or the intrinsic element of equipment.In the absence of more restrictions, being not precluded is including institute
State in process, method, product or the equipment of element that there is also other identical or equivalent elements.For convenience of description, it retouches
It is divided into various modules when stating apparatus above with function to describe respectively.It certainly, can be each mould when implementing this specification embodiment
The function of block is realized in the same or multiple software and or hardware, and the module of same function can also will be realized by multiple sons
Combination realization of module or subelement etc..The apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.The present invention be referring to according to the method for the embodiment of the present invention,
Equipment (system) and the flowchart and/or the block diagram of computer program product describe.It should be understood that can be referred to by computer program
Enable process in each flow and/or block and flowchart and/or the block diagram in implementation flow chart and/or block diagram and/
Or the combination of box.Can provide these computer program instructions to general purpose computer, special purpose computer, Embedded Processor or its
The processor of his programmable data processing device is to generate a machine, so that being handled by computer or other programmable datas
The instruction that the processor of equipment executes generates for realizing in one side of one or more flows of the flowchart and/or block diagram
The device for the function of being specified in frame or multiple boxes.It will be understood by those skilled in the art that the embodiment of this specification can provide for
Method, system or computer program product.Therefore, it is real that complete hardware embodiment, complete software can be used in this specification embodiment
Apply the form of example or embodiment combining software and hardware aspects.Moreover, this specification embodiment can be used in one or more
It wherein include computer-usable storage medium (the including but not limited to magnetic disk storage, CD- of computer usable program code
ROM, optical memory etc.) on the form of computer program product implemented.Each embodiment in this specification, which is all made of, passs
Into mode describe, the same or similar parts between the embodiments can be referred to each other, and each embodiment stresses
It is the difference from other embodiments.For system embodiment, since it is substantially similar to the method embodiment,
So being described relatively simple, the relevent part can refer to the partial explaination of embodiments of method.In the description of this specification, join
The description for examining term " one embodiment ", " some embodiments ", " example ", " specific example " or " some examples " etc. means to tie
Close the embodiment or example particular features, structures, materials, or characteristics described are contained in this specification embodiment at least one
In a embodiment or example.In the present specification, schematic expression of the above terms are necessarily directed to identical implementation
Example or example.In addition, without conflicting with each other, those skilled in the art can be by difference described in this specification
The feature of embodiment or example and different embodiments or examples is combined.The foregoing is merely this specification implementations
The embodiment of example, is not limited to this specification embodiment.To those skilled in the art, this specification is implemented
Example can have various modifications and variations.All any modifications made within the spirit and principle of this specification embodiment are equal
Replacement, improvement etc., should be included within the scope of the claims of this specification embodiment.
Claims (10)
1. a kind of charging pile failure cause diagnostic method characterized by comprising
The fault type of the target charging pile is obtained when target charging pile breaks down；
Preset Bayesian network model is inputted using the fault type of the target charging pile as forecast sample, and by the pattra leaves
Fault type corresponding failure cause diagnostic result of the output of this network model as the target charging pile；
Wherein, the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table, and institute
The topological structure of Bayesian network is stated for indicating between each fault type of charging pile and each failure cause diagnostic result
Corresponding relationship.
2. charging pile failure cause diagnostic method according to claim 1, which is characterized in that further include:
According to the various faults type of charging pile and its corresponding known fault cause diagnosis as a result, generating training sample set；
Using the training sample set, the topological structure of Bayesian network is established based on corresponding score function and searching algorithm；
The conditional probability at each node in the topological structure of the Bayesian network is determined based on Maximum Likelihood Estimation, is obtained
To the conditional probability table of each node.
3. charging pile failure cause diagnostic method according to claim 2, which is characterized in that described according to the more of charging pile
Kind fault type and its corresponding known fault cause diagnosis are as a result, generate training sample set, comprising:
From at least a data in the telemetry, remote signalling data power module monitoring data and transaction data of electric system
Extract the history data of multiple charging piles；
The corresponding charging pile fault signature data of various faults type of charging pile, and root are extracted in the history data
Charging pile fault indices body is established according to the subordinate relation between the corresponding charging pile fault signature data of various fault types
System；
The corresponding charging pile fault signature data of the charging pile fault indices body are pre-processed；
Training sample set is generated according to charging pile fault signature data after pretreatment.
4. charging pile failure cause diagnostic method according to claim 3, which is characterized in that described to the charging pile event
The corresponding charging pile fault signature data of barrier index system are pre-processed, comprising:
Data cleansing and/or attitude layer are carried out to the corresponding charging pile fault signature data of the charging pile fault indices system
Processing；
Data transformation will be carried out through data cleansing and/or attitude layer treated charging pile fault signature data.
5. a kind of charging pile failure cause diagnostic device characterized by comprising
The fault type of target charging pile obtains module, for obtaining the target charging pile when target charging pile breaks down
Fault type；
Target faults cause diagnosis module, it is preset for being inputted using the fault type of the target charging pile as forecast sample
Bayesian network model, and the corresponding failure of fault type by the output of the Bayesian network model as the target charging pile
Cause diagnosis result；
Wherein, the Bayesian network model include Bayesian network topological structure and corresponding conditional probability table, and institute
The topological structure of Bayesian network is stated for indicating between each fault type of charging pile and each failure cause diagnostic result
Corresponding relationship.
6. charging pile failure cause diagnostic device according to claim 5, which is characterized in that further include:
Training sample set generation module, for according to charging pile various faults type and its corresponding known fault cause diagnosis
As a result, generating training sample set；
Bayesian Network Topology Structures establish module, for applying the training sample set, based on corresponding score function and search
Rope algorithm establishes the topological structure of Bayesian network；
Conditional probability obtains module, in the topological structure for determining the Bayesian network based on Maximum Likelihood Estimation
Conditional probability at each node obtains the conditional probability table of each node.
7. charging pile failure cause diagnostic device according to claim 6, which is characterized in that the training sample set generates
Module includes:
History data acquiring unit, for from electric system telemetry, remote signalling data power module monitoring data and
The history data of multiple charging piles is extracted at least a data in transaction data；
Charging pile fault indices Establishing unit, for extracting the various faults class of charging pile in the history data
The corresponding charging pile fault signature data of type, and according between the corresponding charging pile fault signature data of various fault types
Subordinate relation establish charging pile fault indices system；
Data pre-processing unit, for being located in advance to the corresponding charging pile fault signature data of the charging pile fault indices body
Reason；
Training sample set generation unit, for generating training sample set according to charging pile fault signature data after pretreatment.
8. charging pile failure cause diagnostic device according to claim 7, which is characterized in that the data pre-processing unit
It is specifically used for:
Data cleansing and/or attitude layer are carried out to the corresponding charging pile fault signature data of the charging pile fault indices system
Processing；
Data transformation will be carried out through data cleansing and/or attitude layer treated charging pile fault signature data.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes the charging pile event of any one of Claims 1-4 when executing described program
The step of hindering cause diagnosis method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
The step of Claims 1-4 described in any item charging pile failure cause diagnostic methods are realized when processor executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416032.4A CN109596913B (en) | 2018-11-26 | 2018-11-26 | Charging pile fault cause diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416032.4A CN109596913B (en) | 2018-11-26 | 2018-11-26 | Charging pile fault cause diagnosis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109596913A true CN109596913A (en) | 2019-04-09 |
| CN109596913B CN109596913B (en) | 2021-06-15 |
Family
ID=65959744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811416032.4A Active CN109596913B (en) | 2018-11-26 | 2018-11-26 | Charging pile fault cause diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109596913B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110091748A (en) * | 2019-05-21 | 2019-08-06 | 广州小鹏汽车科技有限公司 | Processing method, device and the vehicle of electric vehicle charging exception |
| CN110232142A (en) * | 2019-06-03 | 2019-09-13 | 国家电网有限公司 | Charging pile fault detection method, system and terminal device |
| CN110909774A (en) * | 2019-11-08 | 2020-03-24 | 海南电网有限责任公司海南输变电检修分公司 | Power transformation equipment heating defect reason distinguishing method based on Bayesian classification |
| CN111122199A (en) * | 2019-12-31 | 2020-05-08 | 新奥数能科技有限公司 | Boiler fault diagnosis method and device |
| CN111337764A (en) * | 2020-02-14 | 2020-06-26 | 重庆国翰能源发展有限公司 | Charging pile fault diagnosis system and method and storage medium |
| CN111461481A (en) * | 2020-02-25 | 2020-07-28 | 国网河南省电力公司电力科学研究院 | Power transmission cable quality analysis method based on neural network |
| CN111797768A (en) * | 2020-07-06 | 2020-10-20 | 华侨大学 | Automatic real-time recognition method and system for multiple reasons of urban road traffic congestion |
| CN112180312A (en) * | 2020-08-24 | 2021-01-05 | 南京航空航天大学 | Current sensor composite fault diagnosis method |
| CN112193112A (en) * | 2020-10-16 | 2021-01-08 | 安徽继远软件有限公司 | Intelligent management method and device for charging piles of electric automobile charging station |
| CN113468806A (en) * | 2021-06-23 | 2021-10-01 | 度普(苏州)新能源科技有限公司 | Fault detection method and device for energy storage charging pile and computer readable storage medium |
| CN113657442A (en) * | 2021-07-08 | 2021-11-16 | 广州杰赛科技股份有限公司 | Fault diagnosis method and device for electric vehicle charging equipment and storage medium |
| CN113887676A (en) * | 2021-12-06 | 2022-01-04 | 中国南方电网有限责任公司超高压输电公司广州局 | Equipment fault early warning method, device, equipment, medium and computer program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598969A (en) * | 2014-11-13 | 2015-05-06 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | High-voltage electrical appliance operation quality evaluation method and system based on neural network |
| CN105225020A (en) * | 2015-11-11 | 2016-01-06 | 国家电网公司 | A kind of running status Forecasting Methodology based on BP neural network algorithm and system |
| CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
| CN108320040A (en) * | 2017-01-17 | 2018-07-24 | 国网重庆市电力公司 | Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm |
| US20180240202A1 (en) * | 2015-08-19 | 2018-08-23 | China Electric Power Research Institute Company Limited | Method of predicting distribution network operation reliability |
-
2018
- 2018-11-26 CN CN201811416032.4A patent/CN109596913B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598969A (en) * | 2014-11-13 | 2015-05-06 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | High-voltage electrical appliance operation quality evaluation method and system based on neural network |
| US20180240202A1 (en) * | 2015-08-19 | 2018-08-23 | China Electric Power Research Institute Company Limited | Method of predicting distribution network operation reliability |
| CN105225020A (en) * | 2015-11-11 | 2016-01-06 | 国家电网公司 | A kind of running status Forecasting Methodology based on BP neural network algorithm and system |
| CN108320040A (en) * | 2017-01-17 | 2018-07-24 | 国网重庆市电力公司 | Acquisition terminal failure prediction method and system based on Bayesian network optimization algorithm |
| CN106779505A (en) * | 2017-02-28 | 2017-05-31 | 中国南方电网有限责任公司 | A kind of transmission line malfunction method for early warning driven based on big data and system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110091748A (en) * | 2019-05-21 | 2019-08-06 | 广州小鹏汽车科技有限公司 | Processing method, device and the vehicle of electric vehicle charging exception |
| CN110232142A (en) * | 2019-06-03 | 2019-09-13 | 国家电网有限公司 | Charging pile fault detection method, system and terminal device |
| CN110909774A (en) * | 2019-11-08 | 2020-03-24 | 海南电网有限责任公司海南输变电检修分公司 | Power transformation equipment heating defect reason distinguishing method based on Bayesian classification |
| CN111122199A (en) * | 2019-12-31 | 2020-05-08 | 新奥数能科技有限公司 | Boiler fault diagnosis method and device |
| CN111337764A (en) * | 2020-02-14 | 2020-06-26 | 重庆国翰能源发展有限公司 | Charging pile fault diagnosis system and method and storage medium |
| CN111461481A (en) * | 2020-02-25 | 2020-07-28 | 国网河南省电力公司电力科学研究院 | Power transmission cable quality analysis method based on neural network |
| CN111797768A (en) * | 2020-07-06 | 2020-10-20 | 华侨大学 | Automatic real-time recognition method and system for multiple reasons of urban road traffic congestion |
| CN111797768B (en) * | 2020-07-06 | 2023-05-12 | 华侨大学 | Automatic real-time identification method and system for multiple reasons of urban road traffic jam |
| CN112180312A (en) * | 2020-08-24 | 2021-01-05 | 南京航空航天大学 | Current sensor composite fault diagnosis method |
| CN112180312B (en) * | 2020-08-24 | 2022-01-04 | 南京航空航天大学 | Current sensor composite fault diagnosis method |
| CN112193112A (en) * | 2020-10-16 | 2021-01-08 | 安徽继远软件有限公司 | Intelligent management method and device for charging piles of electric automobile charging station |
| CN113468806A (en) * | 2021-06-23 | 2021-10-01 | 度普(苏州)新能源科技有限公司 | Fault detection method and device for energy storage charging pile and computer readable storage medium |
| CN113657442A (en) * | 2021-07-08 | 2021-11-16 | 广州杰赛科技股份有限公司 | Fault diagnosis method and device for electric vehicle charging equipment and storage medium |
| CN113887676A (en) * | 2021-12-06 | 2022-01-04 | 中国南方电网有限责任公司超高压输电公司广州局 | Equipment fault early warning method, device, equipment, medium and computer program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109596913B (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109596913A (en) | Charging pile failure cause diagnostic method and device | |
| Esenogho et al. | Integrating artificial intelligence Internet of Things and 5G for next-generation smartgrid: A survey of trends challenges and prospect | |
| CN110796368B (en) | Bayesian network-based dynamic risk assessment method and device for community power distribution network | |
| Zhao et al. | Power system fault diagnosis based on history driven differential evolution and stochastic time domain simulation | |
| Di Giorgio et al. | A Bayesian network-based approach to the critical infrastructure interdependencies analysis | |
| CN109933953B (en) | Power distribution network switch state identification method based on probability map model | |
| Sudhakar et al. | Restoration of power network–a bibliographic survey | |
| CN102916431A (en) | Assisted decision making method for load transfer in regional power grid | |
| CN104934968A (en) | Multi-agent based distribution network disaster responding recovery coordinate control method and multi-agent based distribution network disaster responding recovery coordinate control device | |
| Jung et al. | Asset management and maintenance: A smart grid perspective | |
| CN109829560A (en) | A kind of power distribution network renewable energy power generation cluster access planing method | |
| Maffei et al. | A cyber-physical systems approach for implementing the receding horizon optimal power flow in smart grids | |
| CN103745080A (en) | Power grid operation human factor reliability assessment method and device based on Bayesian model | |
| Guo et al. | Evidence-based approach to power transmission risk assessment with component failure risk analysis | |
| Mohammadi et al. | Synthetic benchmarks for power systems | |
| Dwivedi et al. | Advancements in enhancing resilience of electrical distribution systems: A review on frameworks, metrics, and technological innovations | |
| Ustun et al. | Extending IEC 61850 communication standard to achieve Internet-of-Things in smartgrids | |
| CN109932617A (en) | A kind of adaptive electric network failure diagnosis method based on deep learning | |
| Abdelmalak et al. | Network reconfiguration for enhanced operational resilience using reinforcement learning | |
| Giraldo et al. | Optimal operation of community energy storage using stochastic gradient boosting trees | |
| Kumar et al. | Optimal reconfiguration of primary power distribution system using modified Teaching learning based optimization algorithm | |
| Davidson et al. | Exploiting intelligent systems techniques within an autonomous regional active network management system | |
| Liu et al. | Evaluation of hurricane impact on failure rate of transmission lines using fuzzy expert system | |
| Salameh | Digital ecosystem for better management of power systems: an application on microgrids | |
| Fenu et al. | A model of assessment of collateral damage on power grids based on complex network theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |