CN108416443A - A kind of method for diagnosing faults and device - Google Patents
A kind of method for diagnosing faults and device Download PDFInfo
- Publication number
- CN108416443A CN108416443A CN201810271217.4A CN201810271217A CN108416443A CN 108416443 A CN108416443 A CN 108416443A CN 201810271217 A CN201810271217 A CN 201810271217A CN 108416443 A CN108416443 A CN 108416443A
- Authority
- CN
- China
- Prior art keywords
- diagnostics
- diagnostic
- data
- networks
- diagnostic data
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The present invention provides a kind of method for diagnosing faults and device, this method includes：Obtain the diagnostic data of targeted diagnostics object；Extract diagnostic rule from the knowledge base being generated in advance, the diagnostic rule includes the diagnosis corresponding to conditions for diagnostics and conditions for diagnostics；The matched targeted diagnostics condition of diagnostic data institute is determined using rete algorithms, and the targeted diagnostics conclusion corresponding to targeted diagnostics condition is determined as to the diagnostic result of targeted diagnostics object.The present invention utilizes the pattern match characteristic of rete algorithms, sacrifices a part of memory headroom to preserve and make full use of the information in pattern matching process, to improve the matching efficiency of overall failure diagnosis, achievees the effect that significantly reduce calculation amount.
Description
Technical field
The present invention relates to fault diagnosises and health control technical field, more specifically to a kind of method for diagnosing faults
And device.
Background technology
Fault diagnosis is with health control (PHM, Prognostic and Health Management) technology as realization
The key technology of the guarantee of equipment autonomously formula, repair, perception and response.And expert system is then most to induce one to note in fault diagnosis field
One of purpose developing direction.
Method for diagnosing faults based on expert system is varied, it can be common that rule-based fault diagnosis mode.Its
Using the mental process for imitating the mankind, the experience of previous expert diagnosis is generalized into rule, and by Heuristic Experience knowledge into
Row reasoning.And due to the rule structure having the same in rule base, convenient for the unified management of format and setting for inference machine
Meter.
But for the rule base of complication system it is very huge with it is complicated, when handling complication system task, regular
It to be occupied with the time and all calculate 90% or more of the time, can not ensure the real-time of processing.
Invention content
In view of this, a kind of method for diagnosing faults of present invention offer and device, to solve rule-based fault diagnosis side
Formula can not ensure the problem of real-time of processing.Technical solution is as follows：
A kind of method for diagnosing faults, including：
Obtain the diagnostic data of targeted diagnostics object；
Diagnostic rule is extracted from the knowledge base being generated in advance, the diagnostic rule includes conditions for diagnostics and the diagnosis item
Diagnosis corresponding to part；
The matched targeted diagnostics condition of diagnostic data institute is determined using rete algorithms, and by the targeted diagnostics condition
Corresponding targeted diagnostics conclusion is determined as the diagnostic result of the targeted diagnostics object.
Preferably, the diagnostic data for obtaining targeted diagnostics object, including：
The raw diagnostic data of targeted diagnostics object is obtained from preset data source；
The raw diagnostic data is subjected to format analysis processing, obtains tentative diagnosis data；
The diagnostic data of fault diagnosis is used for from the tentative diagnosis extracting data.
Preferably, the process of knowledge base is generated in advance, including：
Obtain fault knowledge information；
Key message of the extraction for fault diagnosis from the fault knowledge information, and using the key message as knowing
Know the content in library.
Preferably, which is characterized in that further include：
Processing is identified to the key message.
Preferably, described to determine the matched targeted diagnostics condition of diagnostic data using rete algorithms, including：
It is the conditions for diagnostics distribution alpha network nodes in alpha networks, wherein the alpha networks are rete
Another part of a part for network, the rete networks is beta networks；
In the beta networks beta network nodes are distributed to constitute the sub- diagnostic data of the diagnostic data, wherein
The beta network nodes distributed and the alpha network nodes for the sub- matched conditions for diagnostics distribution of diagnostic data
It is corresponding；
The attended operation for executing connecting node in the beta networks is examined with obtaining the matched target of the diagnostic data institute
Broken strip part.
Preferably, further include：
The diagnostic result is explained.
A kind of trouble-shooter, including：Data acquisition module, Rule Extraction module and fault diagnosis module；
The data acquisition module, the diagnostic data for obtaining targeted diagnostics object；
The Rule Extraction module, for extracting diagnostic rule, the diagnostic rule packet from the knowledge base being generated in advance
Include the diagnosis corresponding to conditions for diagnostics and the conditions for diagnostics；
The fault diagnosis module, for determining the matched targeted diagnostics item of the diagnostic data institute using rete algorithms
Part, and the targeted diagnostics conclusion corresponding to the targeted diagnostics condition is determined as to the diagnostic result of the targeted diagnostics object.
Preferably, the data acquisition module, is specifically used for：
The raw diagnostic data of targeted diagnostics object is obtained from preset data source；The raw diagnostic data is subjected to lattice
Formula processing, obtains tentative diagnosis data；The diagnostic data of fault diagnosis is used for from the tentative diagnosis extracting data.
Preferably, the fault diagnosis module, is specifically used for：
It is the conditions for diagnostics distribution alpha network nodes in alpha networks, wherein the alpha networks are rete
Another part of a part for network, the rete networks is beta networks；It is the composition diagnosis in the beta networks
The sub- diagnostic datas of data distributes beta network nodes, wherein the beta network nodes distributed be the sub- diagnosis
Data the distribution of matched conditions for diagnostics alpha network nodes it is corresponding；Execute the company of connecting node in the beta networks
Operation is connect, to obtain the matched targeted diagnostics condition of the diagnostic data institute.
Preferably, further include：Illustrate module；
The explanation module, for the diagnostic result to be explained.
Compared to the prior art, what the present invention realized has the beneficial effect that：
A kind of method for diagnosing faults and device provided by the invention, this method are special using the pattern match of rete algorithms above
Property, a part of memory headroom is sacrificed to preserve and make full use of the information in pattern matching process, to improve overall failure diagnosis
Matching efficiency, achieve the effect that significantly reduce calculation amount.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the method flow diagram of method for diagnosing faults provided in an embodiment of the present invention；
Fig. 2 is the Part Methods flow chart of method for diagnosing faults provided in an embodiment of the present invention；
Fig. 3 is another part method flow diagram of method for diagnosing faults provided in an embodiment of the present invention；
Fig. 4 is another Part Methods flow chart of method for diagnosing faults provided in an embodiment of the present invention；
Fig. 5 is the another method flow chart of method for diagnosing faults provided in an embodiment of the present invention；
Fig. 6 is the another method flow chart of method for diagnosing faults provided in an embodiment of the present invention；
Fig. 7 is the structural schematic diagram of trouble-shooter provided in an embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Rete algorithms：It is " net " in Latin language, it is Charles doctors Forgy to have the meaning of network, Rete algorithms
One algorithm of invention in 1974.
Rete networks：Network in rete algorithms is known as rete networks to be distinguished with the network of other algorithms；
Alpha networks：Alpha is Greek alphabet, has the meaning of " first, first part ", rete networks that can be divided into
Two parts, first part are known as alpha networks；
Beta networks：Beta is Greek alphabet, has the meaning of " second, second part ", rete networks that can be divided into two
A part, second part are known as beta networks.
The embodiment of the present invention provides a kind of method for diagnosing faults, and the method flow diagram of this method is as shown in Figure 1, including as follows
Step：
S10 obtains the diagnostic data of targeted diagnostics object；
In the present embodiment, diagnostic data can be obtained directly from preassigned data source, certainly, effectively be examined to obtain
Disconnected data, reuse after can also pre-processing.
During specific implementation, the process of step S10 " diagnostic data for obtaining targeted diagnostics object " can be adopted specifically
With following steps, method flow diagram is as shown in Figure 2：
S101 obtains the raw diagnostic data of targeted diagnostics object from preset data source；
In practical applications, diagnostic data may there are many data sources, such as：Data historian data, Ethernet UDP
Message data, Ethernet TCP message data, various bus datas etc., in addition, the data mode of diagnostic data is there is also a variety of,
Such as analog data, digital data etc..
Raw diagnostic data is carried out format analysis processing, obtains tentative diagnosis data by S102；
In order to avoid developing the data-interface of diversified forms, while being wanted to meet bandwidth, real-time, scalability etc.
It asks, data network will be using ripe DDS middleware Technologies.Data publication in DDS standard criterions Real-Time Distributed System passes
The interface passed and received and behavior define data-centered publish/subscribe mechanism, provide one with it is platform-independent
Data model so that data can be issued efficiently and reliably in Real-Time Distributed System, it be mainly used in requirement high-performance,
Key task field predictable and that resource is effectively used.
In the present embodiment, the various types of diagnostic datas obtained are published to according to established form in DDS networks, with
Just data needed for neatly subscribing to.
S103 is used for the diagnostic data of fault diagnosis from tentative diagnosis extracting data；
In the present embodiment, diagnostic data can be parsed into the data structure of specific meaning according to the definition of interface protocol,
And therefrom extract valid data for fault diagnosis.
S20, extracts diagnostic rule from the knowledge base being generated in advance, and the diagnostic rule includes conditions for diagnostics and described examines
Diagnosis corresponding to broken strip part；
Knowledge base is the storing mechanism of knowledge, is examined for principle diagnostic rule, the empirical of expert in field of storage
Disconnected rule and related diagnostic data etc..The problem of expert system solution procedure be by the knowledge in knowledge base come simulate specially
The mode of thinking of family, therefore, knowledge base is the whether superior key point of expert system quality, the i.e. quality of knowledge in knowledge base
Decide the quality level of expert system with quantity.
And the knowledge acquisition in knowledge base is by the process that Knowledge conversion in objective world is knowledge in expert system, it is
The indispensable part of expert system, basic task are knowledge to be input in knowledge base, and be responsible for maintaining the one of knowledge
Cause property and integrality, it is established that knowledge base of good performance.
In the present embodiment, as shown in figure 3, knowledge base generating process is as follows：
S201 obtains fault knowledge information；
Knowledge engineer obtains fault knowledge information from corresponding knowledge source first, then passes through human-computer interaction interface typing；
S202, key message of the extraction for fault diagnosis from fault knowledge information, and using key message as knowledge
The content in library；
In the present embodiment, key message of the extraction for fault diagnosis from fault knowledge information, including failure cause
Each component, the fault condition of each element, the faulty equipment of each element syntagmatic and failure conclusion, fault mode,
The contents such as repair suggestion, and using key message as the content of knowledge base.
And in order to improve the matching efficiency of fault diagnosis, while convenient for the management of knowledge base, in the knowledge base life shown in Fig. 3
Further include following steps on the basis of process, method flow diagram is as shown in Figure 4：
S203 is identified processing to key message；
In the present embodiment, by the content of knowledge base to identify, such as code name format management, such as " XXX equipment " is deposited
Storage is " D1 ", " XXX sensors " is stored as " S4 ", is stored as the fault mode of equipment " FM-D1-M1 " etc..
Further, the correspondence of each code name and corresponding contents can be stored into associated container, to realize failure
Diagnostic result is translated as meeting the diagnostic result of human language custom by code name.Which achieves human knowledge is converted established practice
Model, efficient, rational expert system knowledge base content.
Knowledge base management process is similar to knowledge base Input Process, on the human-computer interaction interface of the present embodiment close friend, energy
Enough hommizations ground explicit knowledge's library content, knowledge engineer such as can easily increase, delete, changing, looking at the knowledge base managements operation.
S30 determines the matched targeted diagnostics condition of diagnostic data institute using rete algorithms, and by the targeted diagnostics
Targeted diagnostics conclusion corresponding to condition is determined as the diagnostic result of the targeted diagnostics object；
In the present embodiment, step S30 can be executed specifically by inference machine, and inference machine is expert system " thinking " mechanism, is
Constitute the core of expert system.Its task is the thought process of simulation field expert, controls and executes the solution to problem.
It can be made inferences using the knowledge in knowledge base by certain inference method and control strategy according to the currently known fact,
It acquires the answer of problem or proves some correctness assumed.To solve the matching occurred when traditional inference machine is directed to complication system
Speed is slow, efficiency is low and can not ensure processing real-time the problem of, the present embodiment introduce rete algorithms inference machine is changed
To regular Fast Match Algorithm before being one kind into, rete algorithms, matching speed is unrelated with fuzzy rules, and rete networks mainly divide
For two parts --- alpha networks and beta networks.
During specific implementation, step S30 " determines the matched targeted diagnostics of the diagnostic data institute using rete algorithms
The process of condition " can specifically use following steps, method flow diagram as shown in Figure 5：
S301 distributes alpha network nodes, wherein the alpha networks are in alpha networks for conditions for diagnostics
Another part of a part for rete networks, the rete networks is beta networks；
In the present embodiment, conditions for diagnostics is stored into the node memory of alpha network nodes, thus by all alpha
Network node rebuilds alpha networks using data flow network.Since this process is static, as long as all conditions for diagnostics are steady
Calmly, it is not widely varied, alpha networks also can kept stable.
S302 distributes beta network nodes, wherein divide in beta networks to constitute the sub- diagnostic data of diagnostic data
The beta network nodes matched are corresponding with for the matched alpha network nodes of conditions for diagnostics distribution of sub- diagnostic data；
Beta networks are made of two types node, respectively beta network nodes and connecting node, beta network nodes
Set after the completion of main storage connecting node matching, connecting node include two input ports, and input respectively needs matched two
A set, and merging work is done by connecting node and is transferred to next connecting node matching use.
In the present embodiment, diagnostic data is split as multiple sub- diagnostic datas first, for example, by diagnosis computer fan
Diagnostic data is divided into " fan electrical current 1A ", " fan voltage 2V ", " fan power 5W " etc..Due to alpha networks in rete networks
Node is one-to-one with beta network nodes, therefore, can pass through the disclosure satisfy that conditions for diagnostics institute of the sub- diagnostic data of determination
Matched alpha network nodes, to determine the beta network nodes for storing diagnostic data.
In the process, if certain sub- diagnostic data meets multiple conditions for diagnostics simultaneously, only from multiple conditions for diagnostics
A foundation as subsequent processing is chosen, selection rule the present embodiment is not specifically limited.
S303 executes the attended operation of connecting node in beta networks, to obtain the matched targeted diagnostics of diagnostic data institute
Condition；
In executing beta networks before the attended operation of connecting node, first alpha network of alpha networks is selected
Node is run, and the next node of alpha networks is then entered by the alpha network nodes, until getting first storage
Otherwise the alpha network nodes for having conditions for diagnostics jump to next and judge path；
During the attended operation of connecting node in executing beta networks, diagnosis that alpha network nodes are stored
Condition is added in the node memory of the corresponding beta network nodes of alpha network nodes；For a beta network nodes institute
The sub- diagnostic data of storage detects connecting node and connects in another beta network nodes if not arriving the reasoning results node
It whether is stored with the sub- diagnostic data of the condition of satisfaction, meets the attended operation then executed in Beta networks, and next beta nets
Network node repeats the step, conversely, being unsatisfactory for, carries out next sub- diagnostic data.And if the beta network nodes are to push away
Result node is managed, then exports the reasoning results.
In some other embodiment, two main features of rete algorithms are utilized --- redundancy of time (Temporal
Redundancy) and structural similarity (Structural Similarity), the efficiency of pattern match is further increased.
Redundancy of time refers to, variation of diagnostic data during rule-based reasoning in actual operation be it is slow,
I.e. in the matching of each rule and executing the period, the fact that real additions and deletions, only accounts for the ratio of very little, because of the fact in working memory
The rule of data influence only accounts for a seldom part, therefore can be recorded in each execution period and temporarily ignore oneself matched mistake
Diagnostic data, it is only necessary to the diagnostic data and affected diagnostic rule that processing has been changed.And structural similarity refers to,
Rete algorithms are much like in view of the conditions for diagnostics of many diagnostic rules, can make full use of this similitude and be calculated to improve
The efficiency of method.
In addition, in some other embodiment, to accommodate, user carries out systematic learning and system maintenance, is shown in Fig. 1
Method for diagnosing faults on the basis of, further include following steps, method flow diagram is as shown in Figure 6：
Diagnostic result is explained in S40.
In the present embodiment, based on ripe explanation engine technology, by analyzing specific Properties of Objects, specific aim develops
Required explanation engine, to the reasoning results of inference machine, i.e. diagnostic result provides necessary explanation, to the acquisition process of diagnostic result
It provides and is described in detail, user is made to become more apparent upon reasoning process, provided a convenient for systematic learning and system maintenance.
In addition, in practical application in industry level, fault diagnosis result may be used not only for itself expert system and show, also
It needs diagnostic result being transferred to other systems uses, display, assessment and management.So in the present embodiment, fault diagnosis result
Can also by diagnostic result with specific mode tissue after, other systems are transferred to by adaptable interface.
Above step S101~step S103 is only step S10 " the acquisition targeted diagnostics pair that the embodiment of the present application discloses
A kind of preferred realization method of the diagnostic data of elephant " process, the specific implementation in relation to this process can be according to the need of oneself
Arbitrary setting is asked, is not limited herein.
Above step S301~step S303 is only " to utilize rete algorithms in the step S30 that the embodiment of the present application discloses
Determine the diagnostic data matched targeted diagnostics condition " process a kind of preferred realization method, the tool in relation to this process
Body realization method can be arbitrarily arranged according to the demand of oneself, not limit herein.
Method for diagnosing faults provided in an embodiment of the present invention, this method utilize the pattern match characteristic of rete algorithms, sacrifice
A part of memory headroom preserves and makes full use of the information in pattern matching process, and the matching to improve overall failure diagnosis is imitated
Rate achievees the effect that significantly reduce calculation amount.
Based on the method for diagnosing faults that above-described embodiment provides, the embodiment of the present invention then examine by the corresponding above-mentioned failure of execution that provides
The device of disconnected method, structural schematic diagram as shown in fig. 7, comprises：Data acquisition module 10, Rule Extraction module 20 and failure are examined
Disconnected module 30；
The data acquisition module 10, the diagnostic data for obtaining targeted diagnostics object；
The Rule Extraction module 20, for extracting diagnostic rule, the diagnostic rule from the knowledge base being generated in advance
Including the diagnosis corresponding to conditions for diagnostics and the conditions for diagnostics；
The fault diagnosis module 30, for determining the matched targeted diagnostics item of the diagnostic data institute using rete algorithms
Part, and the targeted diagnostics conclusion corresponding to the targeted diagnostics condition is determined as to the diagnostic result of the targeted diagnostics object.
In some other embodiment, data acquisition module 10 is specifically used for：
The raw diagnostic data of targeted diagnostics object is obtained from preset data source；The raw diagnostic data is subjected to lattice
Formula processing, obtains tentative diagnosis data；The diagnostic data of fault diagnosis is used for from the tentative diagnosis extracting data.
In some other embodiment, the Rule Extraction module 20 for knowledge base to be generated in advance is specifically used for：
Obtain fault knowledge information；Key message of the extraction for fault diagnosis from the fault knowledge information, and will
Content of the key message as knowledge base.
In some other embodiment, Rule Extraction module 20 is additionally operable to：
Processing is identified to the key message.
In some other embodiment, fault diagnosis module 30 is specifically used for：
It is the conditions for diagnostics distribution alpha network nodes in alpha networks, wherein the alpha networks are rete
Another part of a part for network, the rete networks is beta networks；It is the composition diagnosis in the beta networks
The sub- diagnostic datas of data distributes beta network nodes, wherein the beta network nodes distributed be the sub- diagnosis
Data the distribution of matched conditions for diagnostics alpha network nodes it is corresponding；Execute the company of connecting node in the beta networks
Operation is connect, to obtain the matched targeted diagnostics condition of the diagnostic data institute.
In some other embodiment, trouble-shooter further includes following module：
Module is illustrated, for diagnostic result to be explained.
Trouble-shooter provided in an embodiment of the present invention sacrifices a part using the pattern match characteristic of rete algorithms
Memory headroom preserves and makes full use of the information in pattern matching process, to improve the matching efficiency of overall failure diagnosis, reaches
To the effect for significantly reducing calculation amount.
A kind of method for diagnosing faults provided by the present invention and device are described in detail above, it is used herein
Principle and implementation of the present invention are described for specific case, and the explanation of above example is only intended to help to understand this
The method and its core concept of invention；Meanwhile for those of ordinary skill in the art, according to the thought of the present invention, specific
There will be changes in embodiment and application range, in conclusion the content of the present specification should not be construed as to the present invention's
Limitation.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment weight
Point explanation is all difference from other examples, and the same or similar parts between the embodiments can be referred to each other.
For the device disclosed in the embodiment, since it is corresponded to the methods disclosed in the examples, so fairly simple, the phase of description
Place is closed referring to method part illustration.
It should also be noted that, herein, relational terms such as first and second and the like are used merely to one
Entity or operation are distinguished with another entity or operation, without necessarily requiring or implying between these entities or operation
There are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that the element that the process, method, article or equipment including a series of elements is intrinsic,
Further include either the element intrinsic for these process, method, article or equipments.In the absence of more restrictions,
The element limited by sentence "including a ...", it is not excluded that in the process, method, article or equipment for including the element
In there is also other identical elements.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (10)
1. a kind of method for diagnosing faults, which is characterized in that including：
Obtain the diagnostic data of targeted diagnostics object；
Diagnostic rule is extracted from the knowledge base being generated in advance, the diagnostic rule includes conditions for diagnostics and conditions for diagnostics institute
Corresponding diagnosis；
The matched targeted diagnostics condition of the diagnostic data institute is determined using rete algorithms, and targeted diagnostics condition institute is right
The targeted diagnostics conclusion answered is determined as the diagnostic result of the targeted diagnostics object.
2. according to the method described in claim 1, it is characterized in that, it is described obtain targeted diagnostics object diagnostic data, including：
The raw diagnostic data of targeted diagnostics object is obtained from preset data source；
The raw diagnostic data is subjected to format analysis processing, obtains tentative diagnosis data；
The diagnostic data of fault diagnosis is used for from the tentative diagnosis extracting data.
3. according to the method described in claim 1, it is characterized in that, the process of knowledge base is generated in advance, including：
Obtain fault knowledge information；
Key message of the extraction for fault diagnosis from the fault knowledge information, and using the key message as knowledge base
Content.
4. according to the method described in claim 3, it is characterized in that, further including：
Processing is identified to the key message.
5. according to the method described in claim 1, it is characterized in that, described determine the diagnostic data using rete algorithms
The targeted diagnostics condition matched, including：
It is the conditions for diagnostics distribution alpha network nodes in alpha networks, wherein the alpha networks are rete networks
A part, another part of the rete networks is beta networks；
Beta network nodes are distributed to constitute the sub- diagnostic data of the diagnostic data, wherein divide in the beta networks
The beta network nodes matched are opposite with the alpha network nodes distributed for the sub- matched conditions for diagnostics of diagnostic data
It answers；
The attended operation for executing connecting node in the beta networks, to obtain the matched targeted diagnostics item of the diagnostic data institute
Part.
6. according to the method described in claim 1, it is characterized in that, further including：
The diagnostic result is explained.
7. a kind of trouble-shooter, which is characterized in that including：Data acquisition module, Rule Extraction module and fault diagnosis mould
Block；
The data acquisition module, the diagnostic data for obtaining targeted diagnostics object；
The Rule Extraction module, for extracting diagnostic rule from the knowledge base being generated in advance, the diagnostic rule includes examining
Diagnosis corresponding to broken strip part and the conditions for diagnostics；
The fault diagnosis module, for determining the matched targeted diagnostics condition of the diagnostic data institute using rete algorithms, and
Targeted diagnostics conclusion corresponding to the targeted diagnostics condition is determined as to the diagnostic result of the targeted diagnostics object.
8. device according to claim 7, which is characterized in that the data acquisition module is specifically used for：
The raw diagnostic data of targeted diagnostics object is obtained from preset data source；By the raw diagnostic data at row format
Reason, obtains tentative diagnosis data；The diagnostic data of fault diagnosis is used for from the tentative diagnosis extracting data.
9. device according to claim 7, which is characterized in that the fault diagnosis module is specifically used for：
It is the conditions for diagnostics distribution alpha network nodes in alpha networks, wherein the alpha networks are rete networks
A part, another part of the rete networks is beta networks；It is the composition diagnostic data in the beta networks
Sub- diagnostic data distribute beta network nodes, wherein the beta network nodes that are distributed be the sub- diagnostic data
The distribution of matched conditions for diagnostics alpha network nodes it is corresponding；Execute the connection behaviour of connecting node in the beta networks
Make, to obtain the matched targeted diagnostics condition of the diagnostic data institute.
10. device according to claim 7, which is characterized in that further include：Illustrate module；
The explanation module, for the diagnostic result to be explained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810271217.4A CN108416443A (en) | 2018-03-29 | 2018-03-29 | A kind of method for diagnosing faults and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810271217.4A CN108416443A (en) | 2018-03-29 | 2018-03-29 | A kind of method for diagnosing faults and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108416443A true CN108416443A (en) | 2018-08-17 |
Family
ID=63132762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810271217.4A Pending CN108416443A (en) | 2018-03-29 | 2018-03-29 | A kind of method for diagnosing faults and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108416443A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245755A (en) * | 2019-06-20 | 2019-09-17 | 贵阳海信网络科技有限公司 | The mantenance data matching process and equipment of faulty equipment |
| CN112666932A (en) * | 2021-03-16 | 2021-04-16 | 奥特酷智能科技(南京)有限公司 | Automatic driving remote diagnosis method and system based on DDS and DoIP technology |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102420700A (en) * | 2011-11-28 | 2012-04-18 | 武汉大学 | Network fault diagnosis system |
| CN104506338A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Fault diagnosis expert system based on decision tree for industrial Ethernet network |
| CN105787563A (en) * | 2014-12-18 | 2016-07-20 | 中国科学院沈阳自动化研究所 | Self-learning mechanism-base fast matching fuzzy reasoning method |
| CN106485594A (en) * | 2016-05-10 | 2017-03-08 | 国网江苏省电力公司南京供电公司 | A kind of main distribution integration incident response decision method |
| CN106533754A (en) * | 2016-11-08 | 2017-03-22 | 北京交通大学 | Fault diagnosis method and expert system for college teaching servers |
| CN106919982A (en) * | 2017-03-20 | 2017-07-04 | 中国科学院沈阳自动化研究所 | A kind of method for diagnosing faults towards semiconductor manufacturing equipment |
-
2018
- 2018-03-29 CN CN201810271217.4A patent/CN108416443A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102420700A (en) * | 2011-11-28 | 2012-04-18 | 武汉大学 | Network fault diagnosis system |
| CN104506338A (en) * | 2014-11-21 | 2015-04-08 | 河南中烟工业有限责任公司 | Fault diagnosis expert system based on decision tree for industrial Ethernet network |
| CN105787563A (en) * | 2014-12-18 | 2016-07-20 | 中国科学院沈阳自动化研究所 | Self-learning mechanism-base fast matching fuzzy reasoning method |
| CN106485594A (en) * | 2016-05-10 | 2017-03-08 | 国网江苏省电力公司南京供电公司 | A kind of main distribution integration incident response decision method |
| CN106533754A (en) * | 2016-11-08 | 2017-03-22 | 北京交通大学 | Fault diagnosis method and expert system for college teaching servers |
| CN106919982A (en) * | 2017-03-20 | 2017-07-04 | 中国科学院沈阳自动化研究所 | A kind of method for diagnosing faults towards semiconductor manufacturing equipment |
Non-Patent Citations (7)
| Title |
|---|
| 刘培国 等: "《电磁兼容现场测量与分析技术》", 30 June 2013 * |
| 张培林 等: "《机械故障信息的量子计算分析及智能诊断》", 31 July 2015 * |
| 徐国虎: "《基于本体的领域知识推理研究》", 31 March 2008 * |
| 曹裕华 等: "《装备体系试验与仿真》", 30 November 2016 * |
| 王瑞 等: "Rete算法在设备故障诊断中的应用研究", 《计算机工程与应用》 * |
| 胡志坤 等: "《变电站物联网与状态监测技术》", 31 July 2014 * |
| 虞和济 等: "《设备故障诊断工程》", 30 June 2001 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245755A (en) * | 2019-06-20 | 2019-09-17 | 贵阳海信网络科技有限公司 | The mantenance data matching process and equipment of faulty equipment |
| CN112666932A (en) * | 2021-03-16 | 2021-04-16 | 奥特酷智能科技(南京)有限公司 | Automatic driving remote diagnosis method and system based on DDS and DoIP technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105787563B (en) | A kind of Rapid matching fuzzy reasoning method based on self-study mechanism | |
| Salman et al. | DeepConf: Automating data center network topologies management with machine learning | |
| Liu et al. | Dynamic adaptive fuzzy Petri nets for knowledge representation and reasoning | |
| CN103020219B (en) | A kind of network expert system tool for electric network failure diagnosis | |
| Perez et al. | Fault diagnosis on electrical distribution systems based on fuzzy logic | |
| Petrova et al. | Towards data-driven sustainable design: decision support based on knowledge discovery in disparate building data | |
| CN103218689A (en) | Analyzing method and analyzing device for operator state assessment reliability | |
| CN100565395C (en) | The autonomy field system of reconfigurable digital controller | |
| CN106291339A (en) | A kind of circuit breaker failure diagnostic expert system based on artificial neural network | |
| CN108416443A (en) | A kind of method for diagnosing faults and device | |
| Choudhary et al. | Optimal coordination of over-current relay in a power distribution network using aggrandized class topper optimization (a-cto) algorithm | |
| Wörn et al. | Diamond: distributed multi-agent architecture for monitoring and diagnosis | |
| Li et al. | A co-simulation method as an enabler for joint analysis and design of MAS-based electrical power protection and communication | |
| Houzé et al. | A generic and modular reference architecture for self-explainable smart homes | |
| CN103258255A (en) | Knowledge discovery method applicable to power grid management system | |
| Bi et al. | Efficient multiway graph partitioning method for fault section estimation in large-scale power networks | |
| Schachinger et al. | An advanced data analytics framework for energy efficiency in buildings | |
| Dounas et al. | Continuous monitoring of adaptive e-learning systems requirements | |
| Valiente-Rocha et al. | Ontology-based expert system for home automation controlling | |
| EP2765667B1 (en) | Method and device for operating a power network | |
| Zamani et al. | AAPNES: A Petri Net expert system realization of adaptive autonomy in smart grid | |
| Zhi-xue et al. | ECA rule modeling language based on UML | |
| da Silva et al. | A framework for expert systems development integrated to a SCADA/EMS environment | |
| CN103105838A (en) | Intelligent logistics electronic selecting system and implementation method | |
| Zhong et al. | Ontology and rule-based reasoning for intelligent predictive manufacturing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180817 |