CN104123609A - Metro construction risk knowledge construction method based on noumenon - Google Patents
Metro construction risk knowledge construction method based on noumenon Download PDFInfo
- Publication number
- CN104123609A CN104123609A CN201410316786.8A CN201410316786A CN104123609A CN 104123609 A CN104123609 A CN 104123609A CN 201410316786 A CN201410316786 A CN 201410316786A CN 104123609 A CN104123609 A CN 104123609A
- Authority
- CN
- China
- Prior art keywords
- risk
- knowledge
- ontology
- risk knowledge
- relation
- 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
Abstract
The invention relates to the field of metro construction risk knowledge construction, and provides a metro construction risk knowledge construction method based on noumenon. The method comprises, based on a risk path obtaining method with a fault tree topological structure, constructing a metro construction risk knowledge network structure, introducing the concept of noumenon to ontologically express and semantically describe risk knowledge, building a risk knowledge ontology library, and thereby achieving clear semantic expression of the construction risk knowledge and mutual relation thereof, and supporting computer understanding and semantic reasoning of the risk knowledge.
Description
Technical field
The present invention relates to subway work risk knowledge and build field, be specifically related to a kind of subway work risk knowledge construction method based on body.
Background technology
In the work progress of subway and various underground workss, carry out risk management most important, as a part for risk management, risk identification is a knowledge-intensive task.Investigation demonstration, mostly risk management is based on supvr's accumulation of experience in early stage and reusing of knowledge.Owing to lacking enough risk knowledges, causing effectively identifying risk, is the modal problem of project implementation phase.
The methods such as traditional risk inventory, risk structure decomposition are generally used, but the risk that is beyond expression, cause the network structure relation between dangerous factor, and risk knowledge associated with each other is divided into isolated knowledge item.In fact associated with each other between risk knowledge, influence each other, form a network structure, and non-unidirectional linear relationship.
, the storage management of risk knowledge was put on record with document form conventionally in the past meanwhile, and do not had to form and can, for computer understanding the data-base recording that can carry out information retrieval, also, not according to the requirement of information management, realize the structurized model management of risk knowledge.
The OO modeling pattern of the many employings of existing risk knowledge model, dependence complicated between risk need to be expressed by the reasoning between relation database table, lacks distinct semantic meaning representation.Moreover this modeling pattern causes follow-up adjustment to need the incidence relation between reconstruct table.
Meanwhile, this knowledge model is also not easy to expansion and shares.Risk knowledge need to participate in coordinating between each side in engineering, and risk knowledge sharing between participant do not supported in traditional knowledge representation.
Body is as the clear and definite standardization explanation of conceptual model, and the structured representation for domain knowledge together with semantic net provides support with reusing.At present, ontology is widely applied in every profession and trade, at building field, has also represented great application advantage.For subway work risk field, the accumulation of historical risk knowledge has significant role to the identification of work progress risk factor from now on and the selection of counter-measure, body and semantic technology are applied in the construction and expression of risk knowledge, to realizing unified structure of this domain knowledge data, are significant.
Summary of the invention
Object of the present invention is just to overcome the weak point in above-mentioned technology, a kind of subway work risk knowledge construction method based on body is provided, Risk Chain (risk path) acquisition methods of the method based on fault tree topological structure, build subway work risk knowledge network structure, and introduce the concept of body, carrying out the ontological of risk knowledge expresses and semantization description, set up risk knowledge ontology library, the distinct semantic meaning representation of realization to construction risk knowledge and mutual relationship thereof, computer understanding and the semantic reasoning of support risk knowledge.
In order to achieve the above object, the technical solution adopted in the present invention is:
A subway work risk knowledge construction method based on body, first obtains the domain knowledge of subway work risk, builds risk monitoring and control library of object.Then the risk factors that extract by fault tree and chain of causation relation thereof, and according to the relation between object and the topological structure of fault tree in risk monitoring and control object territory, build risk knowledge storehouse and the case library of subway work network structure.Then engineering risk Domain Modeling is entered to ontology model, form engineering construction risk ontology library, described ontology library, based on three layers of framework, is respectively that meta-ontology, risk knowledge represent body, example body.Wherein meta-ontology has defined the meta-model of risk knowledge, has expressed abstract concept and the relation thereof of risk knowledge, for the semantic expressiveness of risk knowledge provides unified expression structure, also for the semantic understanding of risk knowledge and reasoning lay the foundation.Risk knowledge represents body, by utilizing the succession of the residing domain-specific knowledge concept of risk monitoring and control object to key concept in meta-ontology and relation, monitored object and risk knowledge thereof is carried out to body and express and obtain.Example body is to express on basis at the body in risk monitoring and control library of object and risk knowledge storehouse, in conjunction with the knowledge of risk case library, express the concrete situation of a certain project practical risk.
Above-mentioned a kind of subway work risk knowledge construction method based on body, comprises the following steps:
(1) analysis field knowledge, extracts concept; Knowledge in risk monitoring and control library of object and the contact between knowledge are analyzed, extracted related notion and relation, set up corresponding concept map.
(2) obtain Risk Chain, build risk knowledge semantic net; Utilize a kind of Risk Chain (risk path) acquisition methods based on risk fault tree topological structure, obtain risk and cause the dependence between dangerous factor and affect relation.Adopt semantic net to carry out the expression of risk knowledge, the field incidence relation by each Risk Chain based on risk monitoring and control object, is connected to become a risk knowledge network map.And adopt semantic network technology to carry out the expression of risk knowledge network, and form a risk knowledge semantic net, realize the distinct semantic meaning representation of risk knowledge and mutual relationship thereof, support computing machine semantic understanding and the reasoning of risk knowledge.
Risk Chain based on risk fault tree topological structure (risk path) acquisition methods is a kind of widely used risk probability and analysis method for reliability.It is using risk case as " top event ", using the reason of the event of generation as " elementary event ", represents the crossing condition of elementary event by logical operator (" with ", "or"), carrys out the relation of adverse events in the expression system of imagery.
Relation in fault tree between " top event ", " intermediate event ", " elementary event " has determined the relation between each node in risk knowledge network.To a certain extent, fault tree is also disclosed and causes the dangerous factor of causing of risk case, so searching that fault tree is Risk Chain provides possibility.
If Fig. 1 is the schematic diagram that a typical fault tree is converted into knowledge network risk chain.
Together with construction risk monitored object, relevant risk and cause dangerous factor, all Risk Chains are woven into a risk knowledge network with together with their risk monitoring and control object.This network, as the knowledge base of field risk monitoring and control, not only comprises the representation of knowledge of demonstration, can also rule-basedly therefrom infer contained implicit knowledge.
(3) formal definitions body; The conceptual model of the risk knowledge network that step (2) is obtained, defines body according to five of body basic first languages, and simple body is with class C and be related to R definition, is expressed as O:{C, R}; More complicated class C for body, be related to R, attribute P, function F, axiom A, example I definition, be expressed as O:{C, R, P, F, A, I}.
(4) build ontology model, realize the expression of risk knowledge; After formal definitions body, utilize Ontology Editing Tool and ontology describing language to build the ontology model of subway work risk knowledge, carry out the semantization of risk knowledge and describe; For risk identification rule, adopt SWRL to express, complete the foundation of risk identification rule base.
Above-mentioned a kind of subway work risk knowledge construction method based on body, in described step (4), Ontology Editing Tool has Prot é g é etc., and ontology describing language has RDF, OWL etc., and ontology rule language has SWRL etc.
The present invention is the subway work risk knowledge construction method based on body, and its feature and meaning are as follows:
The knowledge such as risk identification, the formulation of risk prediction scheme are carried out to domination to be expressed, and utilize semantic network to carry out the expression of association knowledge between risk, make the system based on such knowledge have intelligent, be convenient to computing machine to the semantic understanding of risk knowledge, reasoning and retrieval, for risk management (identification) activity provides knowledge support.The foundation of risk semantic network, is convenient to risk manager and grasps domain knowledge, and the interrelated and impact between visual assurance risk, has improved risk identification, the ability of control.Be conducive to the utilization of engineering risk management and control knowledge, improve risk management and control performance.
Accompanying drawing explanation
Fig. 1 is converted into Risk Chain figure by fault tree in the inventive method.
Fig. 2 is the inventive method risk monitored object storehouse and risk knowledge storehouse associated diagram.
Fig. 3 is towards the three layer model frame diagram of subway engineering risk analysis and monitoring in the inventive method.
Fig. 4 builds the block diagram of subway work risk knowledge ontology library in the inventive method.
Fig. 5 is risk knowledge and the dependence graph thereof obtaining in the inventive method in Risk Chain.
Fig. 6 is the implementing platform figure under Prot é g é environment in the inventive method.
Fig. 7 is deep basal pit example body sectional drawing in the inventive method.
Embodiment
Below in conjunction with drawings and Examples, the invention will be further described.
The classification of subway work risk knowledge and ontology knowledge:
Subway work risk knowledge based on body builds, that comprised risk monitoring and control object and risk knowledge etc. are provided conceptual model and carry out clear and definite Formal Specification explanation, also the chain of causation relation of the relation between object in risk monitoring and control library of object and the risk knowledge that extracts by fault tree is described simultaneously, the logic between knowledge, knowledge store and knowledge application process are integrated as a whole.
The present invention, according to the domain knowledge of subway construction risk, has built risk monitoring and control library of object and risk knowledge storehouse, as shown in Figure 2;
Risk monitoring and control library of object comprises such as construction technology, the construction key element of the various possible occurrence risk such as object and working sources of constructing and the relation between these key elements in work progress.
The contents such as the consequence that risk knowledge storehouse comprises risk, causes dangerous factor, risk-aversion measure, risk are possible and risk identification rule.
By Fault Tree Analysis, extract risk knowledge, and transform to Risk Chain, in conjunction with risk monitoring and control object, form a risk knowledge network interweaving.While describing input and output event relation in fault tree, there is multiple logical symbol, such as " with ", "or", distance etc.The present invention does not consider the difference between these relations, only considers the levels element that topological structure and object properties " Cause " contact, and by specific rules, the Boolean logic between these elements is carried out to modeling.As event in Fig. 1 " E4 " and " E5 ", if two events in same rank and be the relation of logical "or", the relation between them can be expressed by setting up two SWRL rules so.In addition, if a node elements in fault tree, occur repeatedly, so only retain the unique node of this element, other relative node elements, can be directly with this unique node association.
According to the relation between object and the topological structure of fault tree in risk monitoring and control object territory, build subway work risk knowledge network structure.The process of expressing according to body and domain knowledge source, the present invention enters ontology model by engineering risk Domain Modeling, form engineering construction risk ontology library, described ontology library is based on three layers of framework: meta-ontology, risk knowledge represent body and example body, as shown in Figure 3.
A. meta-ontology has defined the meta-model of risk knowledge, has expressed abstract concept and the relation thereof of risk knowledge, for the semantic expressiveness of risk knowledge provides unified expression structure, also for the semantic understanding of risk knowledge and reasoning lay the foundation.
B. risk knowledge represents body, by utilizing the succession of the residing domain-specific knowledge concept of risk monitoring and control object to key concept in meta-ontology and relation, monitored object and risk knowledge thereof is carried out to body and express and obtain.
C. example body, is to express on basis at the body in risk monitoring and control library of object and risk knowledge storehouse, in conjunction with the knowledge of risk case library, expresses the risk example in the concrete situation of a certain project.
Build the concrete steps of subway work risk knowledge body:
As shown in Figure 4, to build subway work risk ontology knowledge concrete steps as follows in the present invention:
(1) analysis field knowledge, extracts concept; Knowledge in risk monitoring and control library of object and the contact between knowledge are analyzed, extracted related notion and relation, set up corresponding concept map.
(2) obtain Risk Chain, build risk knowledge semantic net; Utilize a kind of Risk Chain (risk path) acquisition methods based on risk fault tree topological structure, (dependence acquisition methods), obtains risk and causes the dependence between dangerous factor and affect relation.Adopt semantic net to carry out the expression of risk knowledge, the field incidence relation by each Risk Chain based on risk monitoring and control object, is connected to become a risk knowledge network map.And adopt semantic network technology to carry out the expression of risk knowledge network, and form a risk knowledge semantic net, realize the distinct semantic meaning representation of risk knowledge and mutual relationship thereof, support computing machine semantic understanding and the reasoning of risk knowledge.
(3) formal definitions body; The conceptual model of the risk knowledge network that step (2) is obtained, defines body according to five of body basic first languages.Due to the complicacy of conceptual model, more complicated class C for body, be related to R, attribute P, function F, axiom A, example I definition, be expressed as O:{C, R, P, F, A, I}.
The class is here mainly derived from the concept in the risk knowledge network obtaining above.For risk monitoring and control object, a construction building product class is comprised of a plurality of construction building product subclasses, or a construction procedure has multiple construction method available.
Relation is mainly derived from the relation between the concept in risk knowledge network.Such as being related to that name is called isPartOf and has represented the integral part relation between construction product, isComposedOf represents the relation that a building construction process is comprised of a plurality of construction procedures, and hasRisk represents that risk monitoring and control object exists relation of potential risk etc.
Attribute is binary relation, has mainly described the engineering attribute information of arrangement and method for construction here, such as engineering parameter, and geometric parameter, time parameter, scheduling parameter etc.; Function refers to a reasoning process, as a risk etc. is released in some set that cause dangerous factor; Axiom is the logic statement that the class in body, attribute, example are carried out; Case representation the risk example of the concrete situation of a certain project.
(4) build ontology model, realize the expression of risk knowledge; After formal definitions body, utilize Ontology Editing Tool and ontology describing language to build the ontology model of subway work risk knowledge.Ontology Editing Tool has Prot é g é etc., and ontology describing language has RDF, OWL etc., and ontology rule language has SWRL etc.User can select a kind of the structure and Description Ontology being applicable to according to the feature that will express knowledge.Then carry out the semantization of risk knowledge and describe, complete the foundation of risk knowledge ontology library.If Fig. 6 is the implementing platform figure under Prot é g é environment.
Except the knowledge of OWL explicit representation, also there is the knowledge of many other types by Rule Expression, by driving rule, can from explicit knowledge, infer some conclusions or implicit information/knowledge.Choose SWRL and represent constraint rule.
Article one, SWRL rule comprises former piece (Body) and consequent (Head) two parts, and they form class, attribute, example and the eigenwert in body.Condition/situation that the former piece of rule expresses possibility and causes risk to occur, once the former piece of rule is met, rule can be triggered and carry out the deduction of risk identification so.After rule is carried out, the new fact of deriving will be stored, the factbase based on new, and the rule that other former pieces are met, the execution that will be triggered successively, this is also the embodiment of connecting between risk semantic network risk chain.
Utilize the combination of concept in body and relation as the former piece of identification risk, meet risk former piece, can infer possible risk, and the risk of identification is carried out associated with monitored object.
The body completing for structure, except carrying out the identification reasoning of risk, can also realize the risk information inquiry based on body, obtains abundanter risk information.
SWRL rule can realize the inquiry to OWL knowledge in the lump with SQWRL.By SWRL, write rule searching and realize inquiry, the Risk Chain that can comprise all possible risk and concrete risk monitoring and control object is searched and is enumerated; Meanwhile, infer the risk occurring in a risk monitoring and control object work progress, also likely appear on other risk monitoring and control objects.
(5) the risk semantic meaning representation model based on constructed, by body, SWRL rule and risk monitoring and control information instances be converted in JESS regulation engine rule and true, then the rule matching with the fact in operation rule storehouse, realize the identification reasoning of risk knowledge in JESS regulation engine, the functions such as the risk knowledge retrieval based on semantic, inquiry.
Class with OWL language representation is corresponding with the template in JESS regulation engine, is similar to the process of object-oriented, for defining the hierarchical structure of class and class.
The example of class in OWL, the fact as OWL-Prot é g é, is converted into the fact in JESS accordingly.Equally, the relation in OWL between example, data value, defined object properties and data attribute also need to be converted into the fact in JESS.SWRL rule is converted to JESS rule by converter SWRL2JESS.By transforming, the semantic reasoning of actual risk carries out in JESS regulation engine.
So far, subway work risk knowledge ontology model has built.The ontology model of building provides the basic structure of risk knowledge management database, also can be used as the data model of risk knowledge Management and application, realizes the data storage of risk identification, historical risk case and risk-aversion etc.; Not only overcome the restriction of risk inventory, and can realize the function of the similar reasoning (CBR) based on case.Meanwhile, by OWL and SWRL language, carry out coding and the semantic tagger of risk knowledge, promoted the applicable realization of merit such as identification reasoning, semantic retrieval of risk knowledge.
Be the example of formal definitions deep basal pit field risk knowledge body (FPO) below:
Adopt six By The Boundary Element Methods, FPO::={Cf, Rf, Pf, Ff, Af, If }
Cf is used for describing the risk knowledge content composition in deep basal pit field, for example the supporting construction in deep-foundation pit engineering can be divided into diaphram wall, drill-pouring piling wall, sheet pile wall, soil nail wall etc., can form turn to Cf:={Cf1, Cf2, Cf3,, diaphram wall also can be divided into groove section and web member, such as Cf1={Cf11, and Cf12}
Rf is used for describing the relation between each concept in deep basal pit domain knowledge, can form turn to Rf:={isPartOf, isComposedOf, and isDirectlyAfter, Cause ....The relation that isPartOf expressed portion belongs to, for example web member belongs to a part for diaphram wall; IsComposedOf represents that a building construction process is comprised of a plurality of construction procedures, such as the work progress of diaphram wall, comprises and constructs construction procedures such as leading wall, grooving, pre-inserted web member; IsDirectlyAfter has represented the ordinal relation of two construction procedures, and for example casting concrete is implemented after cleaning web member completes; Cause represents that causes the relation that dangerous factor may cause risk, and for example web member fracture may cause the risk of subway diaphragm wall seepage, by " Cause " each other between risk factors, forms the network structure of a venture influence.
Pf has described the community set of deep basal pit domain knowledge concept, these attribute descriptions the engineering attribute information of arrangement and method for construction, comprise engineering parameter, geometric parameter, time parameter, scheduling parameter etc., can form turn to Pf:={Pf1, Pf2, Pf3,, such as foundation ditch bottom soil property classification, foundation ditch bottom groundwater depth etc.
What Ff described is some rules and the reasoning of deep basal pit field risk knowledge, form turns to Ff:={preFf, and resFf} represents if(preFf) then (resFf), preFf is the set of a plurality of concept element, the result that resFf infers for these concept element.As the reasoning and judging to diaphram wall risk of leakage, if(web member mixes earth & web member fracture) there is risk of leakage in then(diaphram wall).
Af:={a} has described and in deep basal pit field, has carried out axiom and the constraint that risk knowledge reasoning relies on.It is the logic statement that the class in body, attribute, example are carried out.For example, before building mixed earth, must clear up underground continuous wall connector, can form following two axioms 1: before casting concrete, must clean web member (joint); Axiom 2: casting concrete only has a preceding activity.Again for example, in the trenching construction of diaphram wall, lifting steel reinforcement cage operation can not be over 6 hours with the interval time of the mixed earth of perfusion.
If:={i} has described the risk instance objects in deep basal pit field.In example foundation ditch example body as shown in Figure 7, foundation pit supporting construction is cast-in-situ bored pile retaining wall, and soil property classification is silty clay, underground flood peak differs from 4 meters, and foundation ditch Soft Soil Layer is not reinforced, stake enter rock, bury than being 0.7, foundation ditch substratum thickness is less than 20cm, conventionally has the husky risk of foundation ditch ground swell.
OWL is a kind ofly used for the formal language of description logic based on semanteme.It has promoted the automated reasoning between knowledge concepts, and provides RDF/XML grammer to represent ontology knowledge, has realized the information interchange of different kens.For example the trenching construction of diaphram wall has three kinds of construction methods: full punched holes type becomes channel process, and grab claw becomes channel process and revolve to scrape out channel process.Part OWL file code as follows generates under the plug-in environment of Prot é g é and OWL-SEditor, and has described these concepts and relation.
<owl:Classrdf:about="# grab-bucket-digging-trench-method">
<rdfs:subClassOfrdf:resource="# digging-trench-method "/>
<owl:disjointWith>
<owl:Classrdf:about="#percussive-drilling-digging-trench-method"/>
</owl:disjointWith>
<owl:disjointWith>
<owl:Classrdf:about="#rotary-drilling-digging-trench-method "/>
</owl:disjointWith>
</owl:Class>
Same, attributive character also can be described by OWL file code.For example attribute isUsedin has transitivity, and its contrary attribute is Use, and its codomain and field of definition are respectively preparation of construction class and construction activities class.Code is as follows:
<owl:ObjectPropertyrdf:about="#isUsedin">
<rdf:type rdf:resource="http://www.w3.org/2002/07/owl#TransitiveProperty"/>
<owl:inverseOf>
<owl:ObjectPropertyrdf:about="#Use"/>
</owl:inverseOf>
<rdfs:domainrdf:resource="#construction-equipment"/>
<rdfs:rangerdf:resource="# construction-activity"/>
</owl:ObjectProperty>
Based on deep basal pit ontology model, the SWRL rule of foundation and risk monitoring and control information instances are converted into rule in JESS regulation engine and true.
Hierarchical relationship between attribute " hasConTask " " hasConProcess " can represent by following JESS template.
(deftemplateowl:Thing(slot name))
(deftemplatehasConTaskowl:Thing)
(deftemplatehasConProcess extends hasConTask)
True Foundation-Pit_Bottom_1, as the example of Foundation-Pit_Bottom class, is converted into the JESS fact.
assert (Foundation-Pit_Bottom (name Foundation-Pit_Bottom_1) )
It is true that true " the Construction-Task has its corresponding Construction-Method " is converted into following JESS.
(assert (hasConMethod Construction-Task Construction-Method))
Risk identification inference rule " Risk_ID_FlowingSand ", is converted into following JESS rule.
(defrule Rule1(Deep-Foundation-Pit(name pt))( BoredPile(name bpile))( Contiguous_pile_wall(name cpw))( isPartOf cpw, pt) (isAssembledOf cpw, bpile)
(forceCall f:0&:(invokeSWRLBuiltIn Rule1 swrlb:StringEquallgnoreCase 0 bpile false))
(forceCall f:1&:(invokeSWRLBuiltIn Rule1 swrlb: equal 0 bpile 0.7))( Foundation-Pit_Bottom(name fpb)) (isPartOf fpb, pt) (hasFoundationPitBottomSoil fpb, "silt")
(forceCall f:2&:(invokeSWRLBuiltIn Rule1 swrlb:StringEquallgnoreCase 0 fpbs true)) (hasBedthickness fpb, thikness)
(forceCall f:3&:(invokeSWRLBuiltIn Rule8 swrlb: lessThan 0 thikness 200))( HGCO:UndergroundWater(name UGWater)) (hasUnderGroundWater( fpb, UGWater) (hasWaterHead UGWater, waterhead)
(forceCall f:4&:(invokeSWRLBuiltIn Rule8 swrlb: lessThan 0 waterhead 4))( Flowing_sand flowingsandrisk)))
=>(assert( hasRisk fpb flowingsandrisk))
Can find out in " hasRisk " of example " Foundation-Pit_Bottom_1 " Information and occur risk example " Flowing_Sand_Risk ", identify the risk of foundation ditch bottom " drift sand ", and in " hasRiskPreventionMeasure " attribute, provide this prevention of risk measure, with this, remind supvr will note the strick precaution of risk, improve the security of constructing.
Utilization respective queries rule, we can find and list risk that deep basal pit field likely occurs and the concrete risk path of risk monitoring and control object.Meanwhile, we also can infer in the work progress of risk monitoring and control object, the risk that may bring to other objects of constructing etc.
Claims (3)
1. the subway work risk knowledge construction method based on body, it is characterized in that: the domain knowledge that first obtains subway work risk, build risk monitoring and control library of object, then the risk factors that extract by fault tree and chain of causation relation thereof, and according to the topological structure of the relation between object and fault tree in risk monitoring and control library of object, build risk knowledge storehouse and the case library of subway work network structure, then engineering risk Domain Modeling is entered to ontology model, form engineering construction risk ontology library, described ontology library is based on three layers of framework, it is respectively meta-ontology, risk knowledge represents body, example body, wherein meta-ontology has defined the meta-model of risk knowledge, abstract concept and the relation thereof of risk knowledge have been expressed, for the semantic expressiveness of risk knowledge provides unified expression structure, also for the semantic understanding of risk knowledge and reasoning lay the foundation, risk knowledge represents body, by utilizing the succession of the residing domain-specific knowledge concept of risk monitoring and control object to key concept in meta-ontology and relation, monitored object and risk knowledge thereof are carried out to body expresses and obtains, example body is to express on basis at the body in risk monitoring and control library of object and risk knowledge storehouse, knowledge in conjunction with risk case library, express the risk example in the concrete situation of a certain project.
2. a kind of subway work risk knowledge construction method based on body according to claim 1, is characterized in that the method comprises the following steps:
(1) analysis field knowledge, extracts concept; Knowledge in risk monitoring and control library of object and the contact between knowledge are analyzed, extracted related notion and relation, set up corresponding concept map;
(2) obtain Risk Chain, build risk knowledge semantic net; Utilize a kind of Risk Chain acquisition methods based on risk fault tree topological structure, to obtain risk, cause the dependence between dangerous factor and affect relation; Adopt semantic net to carry out the expression of risk knowledge, field incidence relation by each Risk Chain based on risk monitoring and control object, be connected to become a risk knowledge network map, and adopt semantic network technology to carry out the expression of risk knowledge network, form a risk knowledge semantic net, realize the distinct semantic meaning representation of risk knowledge and mutual relationship thereof, support computing machine semantic understanding and the reasoning of risk knowledge;
(3) formal definitions body; The conceptual model of the risk knowledge network that step (2) is obtained, defines body according to five of body basic first languages, and simple body is with class C and be related to R definition, is expressed as O:{C, R}; More complicated class C for body, be related to R, attribute P, function F, axiom A, example I definition, be expressed as O:{C, R, P, F, A, I};
(4) build ontology model, realize the expression of risk knowledge; After formal definitions body, utilize Ontology Editing Tool and ontology describing language to build the ontology model of subway work risk knowledge, carry out the semantization of risk knowledge and describe, complete the foundation of risk knowledge ontology library, for risk identification rule, adopt SWRL to express.
3. a kind of subway work risk knowledge construction method based on body according to claim 1, it is characterized in that: in described step (4), Ontology Editing Tool adopts Prot é g é, and ontology describing language adopts RDF or OWL, and ontology rule language adopts SWRL.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410316786.8A CN104123609A (en) | 2014-07-05 | 2014-07-05 | Metro construction risk knowledge construction method based on noumenon |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410316786.8A CN104123609A (en) | 2014-07-05 | 2014-07-05 | Metro construction risk knowledge construction method based on noumenon |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104123609A true CN104123609A (en) | 2014-10-29 |
Family
ID=51769011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410316786.8A Pending CN104123609A (en) | 2014-07-05 | 2014-07-05 | Metro construction risk knowledge construction method based on noumenon |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104123609A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335488A (en) * | 2015-10-16 | 2016-02-17 | 中国南方电网有限责任公司电网技术研究中心 | Knowledge base construction method |
| CN105989097A (en) * | 2015-02-12 | 2016-10-05 | 北京仿真中心 | Ontology-based knowledge base query method and system |
| CN106991627A (en) * | 2017-03-28 | 2017-07-28 | 广西师范大学 | The distributed intelligence tutoring system acted on behalf of based on domain body and more |
| CN108345994A (en) * | 2018-02-05 | 2018-07-31 | 华中科技大学 | A kind of acquisition of work progress security knowledge, expression and the course monitoring method of structuring |
| CN109189866A (en) * | 2018-08-22 | 2019-01-11 | 北京大学 | A kind of method and system constructing equipment failure diagnostic field ontologies knowledge base |
| CN110807580A (en) * | 2019-10-25 | 2020-02-18 | 上海建科工程咨询有限公司 | Method for analyzing key safety risk of super high-rise construction machinery based on complex network |
| CN113535978A (en) * | 2021-07-13 | 2021-10-22 | 北京交通大学 | Construction method of rail transit system operation risk ontology |
| CN113570214A (en) * | 2021-07-13 | 2021-10-29 | 上海核工程研究设计院有限公司 | Nuclear power project risk network diagram analysis technology implementation method |
| CN113792157A (en) * | 2021-09-14 | 2021-12-14 | 哈尔滨工业大学 | Domain mechanism-oriented knowledge base construction method |
| CN114694098A (en) * | 2022-04-02 | 2022-07-01 | 四川大学 | Power grid infrastructure construction risk control method based on image recognition and knowledge graph |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339428A (en) * | 2011-10-28 | 2012-02-01 | 合肥工业大学 | Large equipment MRO (maintenance repair operating) knowledge construction method based on large equipment |
| CN102999695A (en) * | 2012-10-31 | 2013-03-27 | 华中科技大学 | Subway construction safety risk identification and evaluation system and working method thereof |
-
2014
- 2014-07-05 CN CN201410316786.8A patent/CN104123609A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339428A (en) * | 2011-10-28 | 2012-02-01 | 合肥工业大学 | Large equipment MRO (maintenance repair operating) knowledge construction method based on large equipment |
| CN102999695A (en) * | 2012-10-31 | 2013-03-27 | 华中科技大学 | Subway construction safety risk identification and evaluation system and working method thereof |
Non-Patent Citations (5)
| Title |
|---|
| 于鑫刚 等: "基于本体的知识库模型研究", 《计算机工程与科学》 * |
| 任宇涛: "基于诊疗系统的本体构建方法的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 余宏亮: "基于工程图纸的地铁车站施工安全风险自动识别研究", 《中国博士学位论文全文数据库工程科技II辑》 * |
| 叶婷婷: "集成情境的地铁施工安全动态辨识知识库研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
| 纪兆辉 等: "基于SWRL和Jess构造语义Web规则及其对策分析", 《淮海工学院学报（自然科学版）》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989097A (en) * | 2015-02-12 | 2016-10-05 | 北京仿真中心 | Ontology-based knowledge base query method and system |
| CN105335488A (en) * | 2015-10-16 | 2016-02-17 | 中国南方电网有限责任公司电网技术研究中心 | Knowledge base construction method |
| CN106991627A (en) * | 2017-03-28 | 2017-07-28 | 广西师范大学 | The distributed intelligence tutoring system acted on behalf of based on domain body and more |
| CN108345994A (en) * | 2018-02-05 | 2018-07-31 | 华中科技大学 | A kind of acquisition of work progress security knowledge, expression and the course monitoring method of structuring |
| CN109189866A (en) * | 2018-08-22 | 2019-01-11 | 北京大学 | A kind of method and system constructing equipment failure diagnostic field ontologies knowledge base |
| CN110807580A (en) * | 2019-10-25 | 2020-02-18 | 上海建科工程咨询有限公司 | Method for analyzing key safety risk of super high-rise construction machinery based on complex network |
| CN110807580B (en) * | 2019-10-25 | 2022-03-04 | 上海建科工程咨询有限公司 | Method for analyzing key safety risk of super high-rise construction machinery based on complex network |
| CN113535978A (en) * | 2021-07-13 | 2021-10-22 | 北京交通大学 | Construction method of rail transit system operation risk ontology |
| CN113570214A (en) * | 2021-07-13 | 2021-10-29 | 上海核工程研究设计院有限公司 | Nuclear power project risk network diagram analysis technology implementation method |
| CN113535978B (en) * | 2021-07-13 | 2024-03-19 | 北京交通大学 | Construction method of rail transit system operation risk ontology |
| CN113792157A (en) * | 2021-09-14 | 2021-12-14 | 哈尔滨工业大学 | Domain mechanism-oriented knowledge base construction method |
| CN114694098A (en) * | 2022-04-02 | 2022-07-01 | 四川大学 | Power grid infrastructure construction risk control method based on image recognition and knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104123609A (en) | Metro construction risk knowledge construction method based on noumenon | |
| Simeone et al. | BIM semantic-enrichment for built heritage representation | |
| Ding et al. | Construction risk knowledge management in BIM using ontology and semantic web technology | |
| Woltert et al. | Modal description logics: modalizing roles | |
| CN111552820A (en) | Water engineering scheduling data processing method and device | |
| Dao et al. | Semantic framework for interdependent infrastructure resilience decision support | |
| Zhou et al. | BIM and ontology-based knowledge management for dam safety monitoring | |
| Godager | Critical review of the integration of bim to semantic web technology | |
| Chen et al. | Integrating knowledge management and BIM for safety risk identification of deep foundation pit construction | |
| CN106682072A (en) | Knowledge management based data mining method for digital archives | |
| CN111475604A (en) | Data processing method and device | |
| Döller et al. | Formalizing conceptual modeling methods with MetaMorph | |
| CN105404637B (en) | Data digging method and device | |
| Stouffs | Constructing design representations using a sortal approach | |
| Kronberger et al. | The Digitalization Journey of the Brage Digital Twin | |
| Simeone et al. | A platform for enriching BIM representation through semantic web technologies | |
| Nguyen et al. | An improved algorithm for mining frequent Inter-transaction patterns | |
| Spaccapietra et al. | Spatio-temporal and multi-representation modeling: a contribution to active conceptual modeling | |
| Bel-Ghaddar et al. | Combining model-driven engineering and sewerage networks: towards a generic representation | |
| Du et al. | City infrastructure ontologies | |
| Wen et al. | Construction and application of a multilevel geohazard domain ontology: A case study of landslide geohazards | |
| Belghaddar et al. | Towards a generic fusion framework for underground networks involving model-driven engineering domain | |
| Mohammadi et al. | An ontological framework for identification of construction resources using BIM information | |
| Closa et al. | Web processing service to describe provenance and geospatial modeling | |
| Agrawal | Ontologies for Structural Engineering Models Ontologien für Tragwerksmodelle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141029 |
|
| RJ01 | Rejection of invention patent application after publication |