CN109636139A - A kind of smart machine method for diagnosing faults based on semantic reasoning - Google Patents
A kind of smart machine method for diagnosing faults based on semantic reasoning Download PDFInfo
- Publication number
- CN109636139A CN109636139A CN201811416463.0A CN201811416463A CN109636139A CN 109636139 A CN109636139 A CN 109636139A CN 201811416463 A CN201811416463 A CN 201811416463A CN 109636139 A CN109636139 A CN 109636139A
- Authority
- CN
- China
- Prior art keywords
- semantic
- smart machine
- reasoning
- data
- rule
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003745 diagnosis Methods 0.000 claims abstract description 32
- 238000012423 maintenance Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000003860 storage Methods 0.000 claims abstract description 6
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000002405 diagnostic procedure Methods 0.000 claims description 2
- 239000002994 raw material Substances 0.000 claims description 2
- 230000003068 static effect Effects 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 4
- 230000003993 interaction Effects 0.000 abstract 1
- 238000004519 manufacturing process Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 235000000332 black box Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2273—Test methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a kind of smart machine method for diagnosing faults based on semantic reasoning, the method is on the basis of the magnanimity manufaturing data generated using the storage of cloud distributed system and quick processing smart machine, Prot é g é mathematics library tools build smart machine semantic model is used first, and loads and edit semantic model by Jena kit；Then equipment real time data is read by JDBC, and the equipment real time data in database is got up with model interaction；Then the custom logic inference rule in Jena, and reasoning from logic is carried out using inference machine, realize the fault diagnosis of smart machine；Finally by fault diagnosis result intelligent visual, and recommend suitable solution.Using the present invention, it is remarkably improved smart machine efficiency of fault diagnosis and level in intelligent plant, shortens plant maintenance duration, maximizes productivity effect.
Description
Technical field
The present invention relates to the fault diagnosis fields of smart machine in intelligent plant, and in particular to a kind of based on semantic reasoning
Smart machine method for diagnosing faults.
Background technique
With the rapid development of the relevant technologies such as Internet of Things, cloud computing and advanced manufacture, intelligence manufacture field is also fast
Speed development.Currently, establishing a kind of intelligent plant based on information physical emerging system is the major way for realizing intelligence manufacture.Intelligence
More and more manufacturing equipments have intelligence in energy factory, precisely fixed such as the mechanical arm of automatic identification product category and quantity
The automatic cruising trolley (AGV) etc. of position, this kind of equipment, instrument or machine with calculation processing ability is known as smart machine.
With the appearance and increase of smart machine, manufactures producing line and increasingly emphasize accurate, efficient, orderly and intelligent production, once go out
Existing equipment performance, which declines or breaks down, is likely to result in serious consequence.Different intelligent equipment is according to its action, work frequency
Different faults may occur for the factors such as rate and self-condition, and typical fault type includes: noise, shake, card machine, crash
Deng.When equipment breaks down, if cannot quick discovering device fault type, and position occurs for positioning failure, it will cause
Maintenance of equipment is difficult and the off-time is too long, finally affects greatly to corporate income.Therefore, a kind of effective intelligence is established
Equipment fault diagnosis method ensures that equipment safety operation is most important.
Currently, equipment fault diagnosis mode depends primarily on system alarm, pass through operator first to plant maintenance personnel
It reports failure, then needs to solve failure by carefully checking failure occurrence type and position, so as to cause production process
Not timing is closed.With the rise of industrial big data and cloud computing, equipment fault diagnosis level is stepped up.Magnanimity history and reality
When manufaturing data for device status monitoring and equipment fault diagnosis provide original material.But how to efficiently use these data simultaneously
Therefrom the potential knowledge of effective acquisition is key to the issue.Although the method for diagnosing faults based on machine learning can have from mass data
Effect obtains potential knowledge, but it very relies on diagnostic model accuracy and data sample integrality.And these methods are most
Belong to black-box model, interpretation is poor, is unfavorable for failure precise positioning.And the method for diagnosing faults based on semantic reasoning is by building
Standby semantic model is erected, associate device real time data can fast implement equipment fault Precise Diagnosis.
Equipment semantic model is substantially to a kind of formalized description of the smart machine of objective reality, and description language is to carry out
The basis of semantic modeling and reasoning.Wherein, more typical description language has the Resource for describing triple data
Description Framework (RDF) language and Web Ontology Language (OWL) convenient for flexible abstract modeling
Language.Building smart machine semantic model firstly the need of take out the concept of smart machine, attribute and its between relationship, then make
Semantic model building is carried out with modeling tool.Currently, including graphical construction method and based on generation using most modeling patterns
The construction method of code.Wherein, mathematics library tool Prot é g é is due to having friendly graphical interfaces and various flexible plug-in units
Function is widely paid close attention to and is used, and user, which only needs to carry out to work on a small quantity, can complete model Primary Construction.And it is based on generation
It is the most famous with the Jena development kit based on JAVA programming language in the construction method of code, not only support semantic model
Increase, delete, look into, change, also support semantic reasoning function.Therefore, flexibly with Prot é g é tool and Jena development kit to semanteme
The realization of inference function is most important.
Summary of the invention
The shortcomings that it is an object of the invention to overcome existing smart machine method for diagnosing faults and deficiency, mention for smart machine
For a kind of smart machine method for diagnosing faults based on semantic reasoning, it is intended to efficiency of fault diagnosis is improved, when shortening producing line halt production
Between, maximize productivity effect.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of smart machine method for diagnosing faults based on semantic reasoning, the described method comprises the following steps:
S1, the magnanimity manufaturing data generated using cloud platform storage and processing smart machine, are subsequent semantic knowledge-base
Building and semantic rules, which are write, provides support；
S2, Prot é g é tools build smart machine semantic model is utilized；
S3, the real time data of smart machine is mapped to semantic model, forms semantic knowledge-base；
S4, customized semantic logic inference rule form custom rule library；
S5, fault diagnosis semantic reasoning is carried out using Jena inference machine；
S6, fault diagnosis result is visualized, and recommends adequate solution.
Further, in step S1, the magnanimity manufaturing data that the smart machine generates includes device history data and sets
Standby real-time status data, on the one hand, the potential rule of machine learning algorithm analytical equipment historical data behind are utilized in cloud platform
Rule, extracts valuable information, provides support for semantic rules writing；On the other hand, using cloud distributed system to setting
Standby real-time status data is quickly integrated and is handled, and provides raw material for the building of semantic knowledge-base；In addition, due to magnanimity
Manufaturing data is to be stored and processed based on distributed non-relational database, and be associated with semantic model needs in cloud platform
Regular structural data, it is therefore desirable to be transferred to the data handled well in relevant database from non-relational database.
Further, in step S2, the detailed process using Prot é g é tools build smart machine semantic model
Are as follows: firstly, take out the concept of Intelligent target equipment, attribute and its between relationship, it is especially desirable to equipment actual capabilities are sent out
Raw fault type is abstracted into different failure concepts, and wherein the relationship between concept and concept, concept and attribute is known as object relationship,
And relationship is known as data relationship between attribute and its value range, object relationship is able to carry out customized according to easy to use, and counts
It can only be selected according to actual needs from predefined type according to relationship；Then, it is constructed using Prot é g é graphical tools semantic
The concept taken out, attribute and relationship are set up according to certain logical relation, complete the preliminary structure of semantic model by model
It builds；Finally, carrying out constraint addition to semantic model by Prot é g é tool, the building of smart machine semantic model is completed.It is typical
Constraint include inheriting (SubClass Of), mutual exclusion (Disjoint With), of equal value (Equivalent To) etc., constraint adds
Add is also directly to be completed by clicking Prot é g é visualization plug-in unit.In addition, Prot é g é also has good interactivity, support
The consistency check of semantic logic.
Further, described that the real time data of smart machine is mapped into semantic model in step S3, form semantic knowledge
The detailed process in library are as follows: on the one hand, extract equipment real-time status data using JAVA database fastening means JDBC；Another party
Face utilizes Jena loading equipemtn semantic model；Then, the mapping of data and model is realized by programming, that is, is completed primary semantic
Model instantiation；In the case where equipment real-time status data constantly flows into, semantic model can associate device real-time status,
Ultimately form the semantic knowledge-base of RDF triple form.
Further, in step S4, the customized semantic logic inference rule forms the specific mistake in custom rule library
Journey are as follows: firstly, Inference Conditions and the reasoning results are gone out according to working experience or the knowledge abstraction excavated from device history data,
Middle Inference Conditions correspond to regulatory body, and the reasoning results correspond to regular head；Then, it is described respectively in the form of RDF triple
Regulatory body and regular head, are separated with " -> " symbol；Finally, being that every kind of fault type is fixed on the basis of meeting objective logic
Adopted one or more inference rule, forms custom rule library.
Specifically, an important step for carrying out semantic reasoning is exactly customized inference rule, more to infer
Potential information.In fact, having contained most basic general rule, example during carrying out semantic modeling using Prot é g é
Such as the transitivity and reflexivity of succession, symmetry and uniqueness of attribute etc., these general rules are also to carry out semantic reasoning
Important foundation.In order to obtain more hiding informations, custom logic rule are carried out according to professional experiences and device history data information
Then, this is also most common rule when carrying out equipment fault diagnosis semantic reasoning.Rule is made of regulatory body and regular head, is advised
Then main body is indicated according to data mapping and basic logic judges and the known knowledge that obtains, is located at the regular left side, regular head then table
Show that inference machine passes through that reasoning from logic obtains as a result, being located at rule the right according to known knowledge.Meet regular normalized written and
It, can several customized rules on the basis of objective logic.But with the increase of custom rule quantity, rule base and mould
Type occurs a possibility that semantic conflict and also increases with it, and needs whether detection resource representation clashes and judgment models at this time
It is whether reasonable with the foundation of rule.In addition, also needing that general rule and the semantic of custom rule is avoided to repeat as far as possible, to reduce mould
The complexity of type improves the efficiency of semantic reasoning.In general, smart machine failure occurrence type and reason are varied, therefore need
Custom rule library is ultimately formed according to a plurality of reasoning from logic rule of the customized addition of failure occurrence type and reason.
Further, described to carry out fault diagnosis semantic reasoning detailed process using Jena inference machine in step S5 are as follows: first
First, it calls Jena API that semantic reasoning rule and original licensed machine are together in series and generates inference machine；Then, pass through static method
Original semantic model and inference machine binding are generated into a new reasoning semantic model, wherein newly-generated semantic model is original language
Under the constraint of adopted model semantics rule, the semantic model that is generated after inference machine reasoning；Finally, carrying out intelligence using inference engine
Smart machine state-detection is rapidly completed by the SPARQL semantic reasoning querying command for writing brief in equipment fault diagnosis reasoning
And failure diagnostic process.
Further, in step S6, the visual emphasis is not only in that the intelligence display to diagnostic result, also exists
In the recommendation of corresponding solution, detailed process are as follows: firstly, the possible outcome to fault diagnosis may occur according to every kind of failure
Property size carry out descending arrangement display；Then, the reason of every kind of failure occurring positions, to improve the effect of subsequent maintenance
Rate；Finally, predefining suitable solution respectively for every kind of fault type to form predefined fault type and counte-rplan
Database, in the actual process, the reason of specifically occurring according to failure recommend suitable solution out, provide for maintenance personnel
With reference to；With the understanding that deepens continuously to equipment fault occurrence type and solution, predefined fault type and counte-rplan
Database also can be more and more perfect.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1, the smart machine method for diagnosing faults provided by the invention based on semantic reasoning, utilizes cloud distributed storage solution
The excavation of the certainly storage and processing problem of smart machine mass data, a large amount of historical datas provides foundation for inference rule formulation,
Also it lays a good foundation for equipment fault Precise Diagnosis；Meanwhile cloud distributed system provides quickly to handle a large amount of real time datas
Important support.
2, the smart machine method for diagnosing faults provided by the invention based on semantic reasoning sets intelligence by domain knowledge
Standby to be abstracted and constructed semantic model, which not only has friendly interpretation, also there is good increment type to increase
Performance and universality；Meanwhile the introducing of logic rules and inference machine improves high efficiency, the accuracy of smart machine fault diagnosis
And intelligence.
3, the smart machine method for diagnosing faults provided by the invention based on semantic reasoning, the semantic model of foundation and in real time
The association of data can not only fast implement the fault diagnosis of smart machine, can also effectively carry out equipment state real-time detection,
Greatly improve the safety of smart machine.
4, the smart machine method for diagnosing faults provided by the invention based on semantic reasoning carries out intelligence to fault diagnosis result
It can visualize, not only clearly show smart machine fault diagnosis result, it is suitable to select also from predefined Breakdown Maintenance strategy
Solution effectively reduces equipment downtime maintenance duration, to guarantee production efficiency.
Detailed description of the invention
Fig. 1 is the flow chart of smart machine method for diagnosing faults of the embodiment of the present invention based on semantic reasoning.
Fig. 2 is smart machine method for diagnosing faults general technical route map of the embodiment of the present invention based on semantic reasoning.
Fig. 3 is the construction method figure of the single smart machine semantic model of the embodiment of the present invention.
Fig. 4 is that the embodiment of the present invention breaks down customized two reasoning from logics of type according to AGV trolley actual capabilities
Regular schematic diagram.
Fig. 5 is the flow chart that Jena of embodiment of the present invention inference machine carries out fault diagnosis reasoning.
Specific embodiment
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Embodiment:
Present embodiments provide a kind of smart machine method for diagnosing faults based on semantic reasoning, the flow chart of the method
As shown in Figure 1, comprising the following steps:
S1, the magnanimity manufaturing data generated using cloud platform storage and processing smart machine, are subsequent semantic knowledge-base
Building and semantic rules, which are write, provides support；
S2, Prot é g é tools build smart machine semantic model is utilized；
S3, the real time data of smart machine is mapped to semantic model, forms semantic knowledge-base；
S4, customized semantic logic inference rule form custom rule library；
S5, fault diagnosis semantic reasoning is carried out using Jena inference machine；
S6, fault diagnosis result is visualized, and recommends adequate solution.
Fig. 2 is the smart machine method for diagnosing faults general technical route map based on semantic reasoning, mainly includes six portions
Point, it is respectively: smart machine real-time Data Transmission and processing, the building of smart machine semantic model, real time data and semantic model
Mapping, the addition of custom logic rule, inference machine carries out the intelligent visual of fault diagnosis reasoning and diagnostic result.
Wherein, it is contemplated that smart machine data transmission real-time and data acquisition integrality, the present embodiment need to be combined
After comparing different information collecting methods, information exchange scheme of the final choice based on OPC-UA unified shader.Magnanimity manufactures number
According to transmitting and being stored in cloud distributed system, mass data is cleaned and handled by efficient parallel processing mode.By
In with the associated data of semantic model being finally structural data, therefore non-relation data need to will be stored in by Sqoop tool
Real time data migration in the HBase of library is into relational database MySQL.Then, it is accessed and is closed using database fastening means JDBC
It is database, is ready for the building of semantic knowledge-base.
Fig. 3 is single smart machine semantic model structure figures, here with AGV automatic cruising trolley common in intelligent plant
For.Firstly, the concept and attribute to smart machine itself are abstracted, and the relationship between defined notion and attribute
(Object Property), and suitable value range (Data Property) is chosen for attribute；Secondly, to equipment phase
Other concepts closed are abstracted, such as product relevant to smart machine, state, and define respective concept and its attribute respectively
Relationship (Object Property) between relationship and concept and concept；Finally, utilizing Prot é g é graphic interface tool pair
Above-mentioned concept, attribute and relationship carry out visual modeling.On the basis of completion smart machine is abstract, lead to too small amount of operation i.e.
The building of achievable single smart machine semantic model.
Fig. 4 is the customized two reasoning from logic rules of type that broken down according to AGV trolley actual capabilities.Wherein, it advises
Then 1 indicate, when detecting that equipment voltage is greater than 220V, operating noise is more than 30dB, while revolving speed per minute more than 1500 turns when,
Jitterbug occurs for the inference machine very possible reasoning equipment；Rule 2 shows when detecting that equipment revolving speed is per minute less than 200
Turn, power is less than 1000W, while waiting time is more than 300s, then card machine failure is occurred for the maximum probability reasoning equipment by inference machine.
It can define any a plurality of rule according to actual needs, but should be noted a possibility that rule is clashed with model, Yi Jigui simultaneously
The then reasonability of logic.
Above-mentioned rule code requirement language description is as shown in Table I, and knowledge description is triple form.The abstract of resource is retouched
The form using uniform resource locator (URL) is stated, rule description is also such.For rule of simplification written form, before can using
Sew the mode of binding, wherein prefix needs to be declared first in file beginning.Rule is made of regulatory body and regular head, and rule is main
Body surface shows the known knowledge obtained according to data mapping and basic logic judgement, is located at the regular left side, regular head then indicates to push away
Reason machine passes through that reasoning from logic obtains as a result, being located at rule the right according to known knowledge.Meeting regular normalized written and objective
On the basis of logic, can several customized regular formation rule libraries, provide foundation for inference machine progress reasoning from logic.
Table I
Fig. 5 is that Jena inference machine quickly carries out fault diagnosis reasoning flow chart.It is first loaded into semantic model and customized language
Secondly rule and register machine binding are generated inference machine by adopted rule, original semantic model and inference machine binding are then generated one
A new semantic model.Meanwhile needing to detect whether smart machine real time data updates or change, it will be new if updating
Data set is mapped on new semantic model, then carries out fault diagnosis to newly-generated RDF data collection using Jena inference machine
Reasoning shows fault type by diagnostic result visual intelligent, and analyze and call and suitably answer other side if breaking down
Case provides support for Breakdown Maintenance.
The above, only the invention patent preferred embodiment, but the scope of protection of the patent of the present invention is not limited to
This, anyone skilled in the art is in the range disclosed in the invention patent, according to the present invention the skill of patent
Art scheme and its patent of invention design are subject to equivalent substitution or change, belong to the scope of protection of the patent of the present invention.
Claims (7)
1. a kind of smart machine method for diagnosing faults based on semantic reasoning, which is characterized in that the described method comprises the following steps:
S1, the magnanimity manufaturing data generated using cloud platform storage and processing smart machine, are constructed for subsequent semantic knowledge-base
It is write with semantic rules and support is provided；
S2, Prot é g é tools build smart machine semantic model is utilized；
S3, the real time data of smart machine is mapped to semantic model, forms semantic knowledge-base；
S4, customized semantic logic inference rule form custom rule library；
S5, fault diagnosis semantic reasoning is carried out using Jena inference machine；
S6, fault diagnosis result is visualized, and recommends adequate solution.
2. a kind of smart machine method for diagnosing faults based on semantic reasoning according to claim 1, it is characterised in that: step
In rapid S1, the magnanimity manufaturing data that the smart machine generates includes device history data and equipment real-time status data, a side
Face utilizes the potential rule of machine learning algorithm analytical equipment historical data behind in cloud platform, extracts valuable letter
Breath provides support for semantic rules writing；On the other hand, equipment real-time status data is carried out using cloud distributed system fast
The integration and processing of speed, provide raw material for the building of semantic knowledge-base；In addition, since magnanimity manufaturing data is in cloud platform
It is stored and processed based on distributed non-relational database, and is associated with semantic model and needs regular structural data, because
The data handled well are transferred in relevant database by this needs from non-relational database.
3. a kind of smart machine method for diagnosing faults based on semantic reasoning according to claim 1, which is characterized in that step
In rapid S2, the detailed process using Prot é g é tools build smart machine semantic model are as follows: firstly, taking out target intelligence
Can the concept of equipment, attribute and its between relationship, it is especially desirable to the equipment actual capabilities type that breaks down is abstracted into difference
Failure concept, wherein the relationship between concept and concept, concept and attribute is known as object relationship, and between attribute and its value range
Relationship is known as data relationship, and object relationship is able to carry out customized according to easy to use, and data relationship can only be from predefined
It is selected according to actual needs in type；Then, using Prot é g é graphical tools construct semantic model, by the concept taken out,
Attribute and relationship are set up according to certain logical relation, complete the Primary Construction of semantic model；Finally, passing through Prot é g é
Tool carries out constraint addition to semantic model, completes the building of smart machine semantic model.
4. a kind of smart machine method for diagnosing faults based on semantic reasoning according to claim 1, which is characterized in that step
It is described that the real time data of smart machine is mapped into semantic model in rapid S3, form the detailed process of semantic knowledge-base are as follows: a side
Face extracts equipment real-time status data using JAVA database fastening means JDBC；On the other hand, Jena loading equipemtn is utilized
Semantic model；Then, the mapping of data and model is realized by programming, that is, completes a semantic model instantiation；In equipment reality
When status data constantly flow into the case where, semantic model can associate device real-time status, ultimately form RDF triple shape
The semantic knowledge-base of formula.
5. a kind of smart machine method for diagnosing faults based on semantic reasoning according to claim 1, which is characterized in that step
In rapid S4, the customized semantic logic inference rule forms the detailed process in custom rule library are as follows: firstly, according to working
Experience or the knowledge abstraction excavated from device history data go out Inference Conditions and the reasoning results, and wherein Inference Conditions correspond to rule
Then main body, the reasoning results correspond to regular head；Then, description rule main body and regular head are distinguished in the form of RDF triple, are used
" -> " symbol separates；Finally, being that every kind of fault type defines one or more reasoning rule on the basis of meeting objective logic
Then, custom rule library is formed.
6. a kind of smart machine method for diagnosing faults based on semantic reasoning according to claim 1, which is characterized in that step
It is described to carry out fault diagnosis semantic reasoning detailed process using Jena inference machine in rapid S5 are as follows: firstly, calling Jena API by language
Adopted inference rule and original licensed machine, which are together in series, generates inference machine；Then, it by original semantic model and is pushed away by static method
The binding of reason machine generates a new reasoning semantic model, wherein newly-generated semantic model is the pact of original semantic model semantics rule
Under beam, the semantic model that is generated after inference machine reasoning；Finally, smart machine fault diagnosis reasoning is carried out using inference engine,
Smart machine state-detection and failure diagnostic process is rapidly completed by the SPARQL semantic reasoning querying command for writing brief.
7. a kind of smart machine method for diagnosing faults based on semantic reasoning according to claim 1, which is characterized in that step
In rapid S6, the visual emphasis is not only in that the intelligence display to diagnostic result, also resides in pushing away for corresponding solution
It recommends, detailed process are as follows: firstly, the possible outcome to fault diagnosis carries out descending row according to the size of every kind of failure possibility occurrence
Column display；Then, the reason of every kind of failure occurring positions, to improve the efficiency of subsequent maintenance；Finally, being every kind of failure
Type predefines suitable solution to form predefined fault type and counte-rplan database, in real process respectively
In, the reason of specifically occurring according to failure, recommends suitable solution out, provides reference for maintenance personnel；With to equipment event
Hinder the understanding that deepens continuously of occurrence type and solution, predefined fault type and counte-rplan database also can be more and more completeer
It is kind.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416463.0A CN109636139A (en) | 2018-11-26 | 2018-11-26 | A kind of smart machine method for diagnosing faults based on semantic reasoning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416463.0A CN109636139A (en) | 2018-11-26 | 2018-11-26 | A kind of smart machine method for diagnosing faults based on semantic reasoning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109636139A true CN109636139A (en) | 2019-04-16 |
Family
ID=66069579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811416463.0A Pending CN109636139A (en) | 2018-11-26 | 2018-11-26 | A kind of smart machine method for diagnosing faults based on semantic reasoning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636139A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111026046A (en) * | 2019-11-06 | 2020-04-17 | 重庆邮电大学 | Production line equipment fault diagnosis system and method based on semantics |
| CN111178603A (en) * | 2019-12-19 | 2020-05-19 | 重庆邮电大学 | Semantic-based industrial production equipment predictive maintenance system |
| CN111583058A (en) * | 2020-03-17 | 2020-08-25 | 国网浙江省电力有限公司杭州供电公司 | Power distribution network security analysis system generation method and device |
| CN111626060A (en) * | 2020-05-21 | 2020-09-04 | 山东师范大学 | Product innovation design method and system based on object field analysis and rule reasoning |
| CN111882084A (en) * | 2020-07-27 | 2020-11-03 | 西门子工厂自动化工程有限公司 | Method and apparatus for performing maintenance on field devices in a plant |
| CN111950197A (en) * | 2020-08-04 | 2020-11-17 | 珠海市鸿瑞信息技术股份有限公司 | Distribution network attack and fault acquisition and analysis system based on artificial intelligence semantics |
| CN112597129A (en) * | 2020-12-21 | 2021-04-02 | 浙江大学 | Automatic construction method of OPC UA information model based on structured database |
| CN113312411A (en) * | 2021-06-22 | 2021-08-27 | 中国电子科技集团公司第十四研究所 | Equipment fault cause diagnosis method based on knowledge graph and rule constraint |
| WO2022120585A1 (en) * | 2020-12-08 | 2022-06-16 | Amazon Technologies, Inc. | Using graph queries to obtain results from machine learning models |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679828A (en) * | 2015-01-19 | 2015-06-03 | 云南电力调度控制中心 | Rules-based intelligent system for grid fault diagnosis |
| CN105302112A (en) * | 2015-10-23 | 2016-02-03 | 中国电子科技集团公司第十研究所 | Intelligent fault diagnosis system for ICNI system |
| CN108519769A (en) * | 2018-04-09 | 2018-09-11 | 电子科技大学 | A kind of rule-based flight control system method for diagnosing faults |
-
2018
- 2018-11-26 CN CN201811416463.0A patent/CN109636139A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679828A (en) * | 2015-01-19 | 2015-06-03 | 云南电力调度控制中心 | Rules-based intelligent system for grid fault diagnosis |
| CN105302112A (en) * | 2015-10-23 | 2016-02-03 | 中国电子科技集团公司第十研究所 | Intelligent fault diagnosis system for ICNI system |
| CN108519769A (en) * | 2018-04-09 | 2018-09-11 | 电子科技大学 | A kind of rule-based flight control system method for diagnosing faults |
Non-Patent Citations (3)
| Title |
|---|
| 任鹏等: "基于本体推理的故障信息关联及诊断应用研究", 《燕山大学学报》 * |
| 李剑峰等: "基于OWL本体和SWRL规则的导弹智能故障诊断研究", 《计算机测量与控制》 * |
| 王劲东等: "基于Jena的电影素材领域本体构建及推理研究", 《计算机技术与发展》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111026046A (en) * | 2019-11-06 | 2020-04-17 | 重庆邮电大学 | Production line equipment fault diagnosis system and method based on semantics |
| CN111178603A (en) * | 2019-12-19 | 2020-05-19 | 重庆邮电大学 | Semantic-based industrial production equipment predictive maintenance system |
| CN111583058A (en) * | 2020-03-17 | 2020-08-25 | 国网浙江省电力有限公司杭州供电公司 | Power distribution network security analysis system generation method and device |
| CN111583058B (en) * | 2020-03-17 | 2023-09-05 | 国网浙江省电力有限公司杭州供电公司 | Method and device for generating power distribution network safety analysis system |
| CN111626060A (en) * | 2020-05-21 | 2020-09-04 | 山东师范大学 | Product innovation design method and system based on object field analysis and rule reasoning |
| CN111626060B (en) * | 2020-05-21 | 2021-05-11 | 山东师范大学 | Product innovation design method and system based on object field analysis and rule reasoning |
| CN111882084A (en) * | 2020-07-27 | 2020-11-03 | 西门子工厂自动化工程有限公司 | Method and apparatus for performing maintenance on field devices in a plant |
| CN111950197A (en) * | 2020-08-04 | 2020-11-17 | 珠海市鸿瑞信息技术股份有限公司 | Distribution network attack and fault acquisition and analysis system based on artificial intelligence semantics |
| WO2022120585A1 (en) * | 2020-12-08 | 2022-06-16 | Amazon Technologies, Inc. | Using graph queries to obtain results from machine learning models |
| CN112597129A (en) * | 2020-12-21 | 2021-04-02 | 浙江大学 | Automatic construction method of OPC UA information model based on structured database |
| CN113312411A (en) * | 2021-06-22 | 2021-08-27 | 中国电子科技集团公司第十四研究所 | Equipment fault cause diagnosis method based on knowledge graph and rule constraint |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636139A (en) | A kind of smart machine method for diagnosing faults based on semantic reasoning | |
| US8610718B2 (en) | Method of visualizing sets of correlated events on a display | |
| CN101989087B (en) | On-line real-time failure monitoring and diagnosing system device for industrial processing of residual oil | |
| CN113853553A (en) | Automatic extraction of asset data from engineering data sources for generation of HMI | |
| CN109785180A (en) | A kind of scene perception system and method towards the twin workshop of number | |
| CN116578040B (en) | Digital twin model construction method, system and terminal for machine tool fault diagnosis | |
| EP2207106A2 (en) | Complex relational database extraction system and method with respective based dynamic data modeling | |
| Liu et al. | Dynamic design method of digital twin process model driven by knowledge-evolution machining features | |
| EP2555109B1 (en) | Search utility program for software developers | |
| CN112084385B (en) | Part-process-equipment association relationship topological view generation method based on digital twinning | |
| CN106354106A (en) | Data processing system based on MES | |
| CN116976043A (en) | Knowledge graph-based intelligent auxiliary decision-making method for SDSS (Standard data System) power grid | |
| CN105759784A (en) | Fault diagnosis method based on data envelopment analysis | |
| CN107908559A (en) | A kind of Test Case Design method and device | |
| CN108319673A (en) | A kind of fault tree construction method based on relational database | |
| CN115718472A (en) | Fault scanning and diagnosing method for hydroelectric generating set | |
| Xiao et al. | Knowledge graph-based manufacturing process planning: A state-of-the-art review | |
| Liu et al. | CNC machine tool fault diagnosis integrated rescheduling approach supported by digital twin-driven interaction and cooperation framework | |
| CN113901231A (en) | Method, device and medium for evolution analysis of knowledge graph | |
| Tao et al. | Advancements and challenges of digital twins in industry | |
| CN102902614B (en) | A kind of dynamic monitoring and intelligent guide method | |
| CN109472484A (en) | A kind of production process exception record method based on flow chart | |
| CN116051069A (en) | Operation and maintenance fault monitoring system modeling method based on knowledge graph and OPC UA protocol | |
| Michael et al. | Research on fault diagnosis expert system of cnc machine tool based on expert knowledge | |
| US10817366B2 (en) | Method and apparatus for tracing common cause failure in integrated drawing |
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: 20190416 |