CN105205537A - Ontology based feature processing technology knowledge representation and inference device and method - Google Patents
Ontology based feature processing technology knowledge representation and inference device and method Download PDFInfo
- Publication number
- CN105205537A CN105205537A CN201510713817.8A CN201510713817A CN105205537A CN 105205537 A CN105205537 A CN 105205537A CN 201510713817 A CN201510713817 A CN 201510713817A CN 105205537 A CN105205537 A CN 105205537A
- Authority
- CN
- China
- Prior art keywords
- feature
- reasoning
- ontology
- knowledge
- machining process
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to an ontology based feature processing technology knowledge representation and inference device which comprises a domain ontology module, a graph parameterization technological ontology modeling module, a general ontology modeling module and an inference module connected in sequence, wherein a data interface is arranged between the graph parameterization technological ontology modeling module and the general ontology modeling module; a plug-in is arranged between the graph parameterization technological ontology modeling module and the general ontology modeling module. In the field of feature processing technology knowledge, the ontology based feature processing technology knowledge representation and inference device utilizes the ontology theory to express feature technology knowledge, can solve the problems that the process type feature processing technology knowledge is difficult in representation and inference and poor in maintainability, and expresses the technology knowledge in a graphical manner to enable a user to master the knowledge maintenance method, to enable knowledge representation to be more vivid, and to enable knowledge maintenance to be more convenient and faster.
Description
Technical field
The present invention relates to expression and the reasoning field of feature machining process knowledge, be specifically related to a kind of device and method of the feature machining Process Knowledge Representation reasoning based on body.
Background technology
Feature machining process knowledge is a very important part in process knowledge system, in three-dimensional process design, the core value of feature machining process knowledge is as Part's Process Route provides the Process ba-sis with reference value, and the feature machining technique utilizing the attribute of feature to infer can ensure that process is economy, meets technological requirement.
Can knowledge representation solve for problem, whether be convenient to program realizes there is significant impact, and the Correct of the structure of knowledge is very crucial, so want the expression pattern of a kind of practicality of Choice and design.Whether the factor that feature process knowledge representation is considered includes, but is not limited to: 1) express accurate and effective, inference rule whether directly perceived, simple, can understand and meet the general thinking of the mankind; 2) whether knowledge is convenient to expansion and is safeguarded; 3) whether knowledge is convenient to computer program realization.
In prior art, the expression of knowledge mainly contains following five kinds:
(1) predicate logic representation: this representation is by after the symbolism such as the object in knowledge, character, situation and relation, utilize predicate well-formed formula and predicate to describe precondition and theorem, whether new problem can infer from precondition then to utilize logical formula to prove.Predicate logic representation is applicable to representing the cause-effect relationship determined between the factual knowledge such as state, attribute, concept of things and things, but can not represent uncertainty knowledge, and Reasoning Efficiency is very low.
(2) production rule representation: this representation production rule form of " IFATHENB " represents the cause-effect relationship of things or knowledge.Production rule representation is applicable to empirical field, and the cause-effect relationship of knowledge is clear and definite, naturally flexible, and be convenient to understand, reasoning process is clear, but is not suitable for expression structure sex knowledge, easily causes rule conflict or shot array.
(3) semantic network representation: this representation adopts network chart to express knowledge, and wherein node represents things, concept and situation etc., and camber line represents internodal relation.Semantic network representation is applicable to the occasion of carrying out relation between the field of reasoning and the process state of things, character, action according to clear and definite classification, naturally direct, meet human thinking's custom, but the network chart of this weak constraint cannot ensure severity and the validity of inference, and the storage of knowledge and retrieval more complicated.
(4) frame representation: this representation framework and groove represent the attribute of practical judgment and object respectively.A framework is made up of one group of groove, and each groove represents an attribute of object, and the value of groove is exactly object's property value.Frame representation is applicable to describe that level is good, inheritance is good and have object in fixed form.When there is multiple inheritance, easily produce ambiguity, and be bad to express process-type knowledge.
(5) parametric procedure figure representation: this representation is a kind of visual knowledge representation method based on parameter list and procedure chart, and the various factors considered in decision process with parameter expression domain expert, expresses procedural knowledge with procedure chart.Parametric procedure figure knowledge representation has visual, parameterized feature, is relatively applicable to knowledge that is dynamic in expression process, Process Character.But when complicated decision process, the definition of procedure chart is too complicated, and the difficulty of knowledge expansion and maintenance is larger.
Feature machining process knowledge is process-type knowledge, has certain field feature, mainly comprises description type knowledge (the job operation collection of feature) and inference type knowledge (relation between feature and characteristic processing method).Stronger incidence relation is had between description type knowledge, as all relevant in characteristic processing method and cutter, lathe, machining precision etc.Inference type knowledge description is more difficult, be not only because knowledge entry total amount is more, and part inference type knowledge does not quantize or objectification, easily produce fuzzy meaning, and partial knowledge has implication.In general, the more difficult implication to feature machining technique of said method carries out reasoning, and the maintainability of knowledge entry and can be inferential poor.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of device and method of the feature machining Process Knowledge Representation reasoning based on body, can solve the problem of difficult, the maintainable difference of feature machining Process Knowledge Representation and reasoning of process-type.
The technical scheme that the present invention solves the problems of the technologies described above is as follows: a kind of device of the feature machining Process Knowledge Representation reasoning based on body, comprise the domain body module, graphic parameter metallization processes Ontology Modeling module, general ontology MBM and the reasoning module that are connected successively, be provided with data-interface between described graphic parameter metallization processes Ontology Modeling module and described general ontology MBM, between described general ontology MBM and described reasoning module, be provided with plug-in unit;
Described domain body module, it forms mechanical processing technique domain body for the process knowledge in field of machining being carried out process knowledge ontology modeling;
Described graphic parameter metallization processes Ontology Modeling module, it forms parameter characteristic processing technology body for mechanical processing technique domain body being carried out modeling, and for parameter characteristic processing technology body provide image conversion feature machining process reasoning rule, also for external process feature is converted into characteristic attribute, also for by examples translating for internal feature job operation be characteristic processing method, form surface job operation tree;
Described general ontology MBM, it is converted into general statistical process ontologies and process reasoning rule, also for characteristic attribute is converted into internal feature example for parameter characteristic processing technology body and image conversion feature machining process reasoning being advised correspondence respectively;
Described reasoning module, it is for carrying out the optimization of hierarchical structure and relation according to process reasoning rule by general statistical process ontologies, excavate the relation between potential concept, obtaining the general feature machining process knowledge ontology of complete optimization, also obtaining as internal feature job operation example for internal feature example being carried out case-based reasoning.
The invention has the beneficial effects as follows: the device of a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention is in feature machining process knowledge field, utilize ontology theory to carry out the expression of feature process knowledge, the problem of difficult, the maintainable difference of feature machining Process Knowledge Representation and reasoning of process-type can be solved; Secondly profit of the present invention graphically expression process knowledge, contribute to the method that user grasps knowledge maintenance, make knowledge representation more vivid, knowledge maintenance is more convenient.
On the basis of technique scheme, the present invention can also do following improvement.
Further, described data-interface is used for carrying out Data Format Transform between graphic parameter metallization processes Ontology Modeling module and described general ontology MBM, and described plug-in unit is used for carrying out exchanges data between general ontology MBM and reasoning module.
Further, described general ontology MBM adopts Prot é g é modeling tool, and described reasoning module adopts Pellet inference machine, and described graphic parameter metallization processes Ontology Modeling module adopts OGPTool.
The beneficial effect of above-mentioned further scheme is adopted to be: the present invention selects to support that the Prot é g é instrument of the OWL second edition and SWRL is as general ontology modeling, this instrument provides user oriented Visual Ontology edit tool on the one hand, graphical body can be converted into OWL form; This instrument is as general utility tool on the other hand, can be as integrated in Pellet, FaCT++, Hermit, Racer etc. with most of inference machine.
Further, described Prot é g é modeling tool and Pellet inference machine all support second edition OWL language and SWRL language, described second edition OWL language is the language of Expressive Features processing technology ontologies, and described SWRL language is the language describing process knowledge inference rule.
Further, based on OWL feature machining process knowledge ontology be expressed as four-tuple, the form of described four-tuple is (knowledge class, knowledge instance, attribute, relation); Expression based on the process knowledge inference rule of SWRL is made up of rules simplify unit, and described regular primitive shape, as function representation, represents function name by class name or relation name, variable with question mark "? " addition of variable name represents; Expression way based on the feature machining process knowledge ontology modeling of OPGTool is bulk junction paper mulberry, example, parameter process flow diagram, constraint rule and calculation expression.
Based on the device of above-mentioned a kind of feature machining Process Knowledge Representation reasoning based on body, the present invention also provides a kind of method of the feature machining Process Knowledge Representation reasoning based on body.
Based on a method for the feature machining Process Knowledge Representation reasoning of body, comprise the following steps,
S1, expresses the process knowledge in field of machining in the device of a kind of feature machining Process Knowledge Representation reasoning based on body described above, obtains the feature machining process knowledge ontology of expressing;
S2, carries out case-based reasoning by the feature machining process knowledge ontology that external process integrate features is expressed in the device of a kind of feature machining Process Knowledge Representation reasoning based on body described above, obtains surface job operation tree.
The invention has the beneficial effects as follows: the inference method of a kind of feature machining process knowledge based on body of the present invention utilizes the feature of body, establish the incidence relation of each key element in feature process knowledge, its process safeguarded only needs to add example on request, its maintenance cost reduces greatly, and the efficiency of maintenance improves greatly.
On the basis of technique scheme, the present invention can also do following improvement.
Further, the specific implementation of step S1 comprises the following steps,
S11, using the process knowledge in mechanical processing technique field as data source, to be characterized as key concept, using ontology as theoretical foundation, carries out process knowledge ontology modeling in domain body module, forms mechanical processing technique domain body;
S12, mechanical processing technique domain body is converted into computer expression mode in OGPTool, and modeling is carried out to the mechanical processing technique domain body of computer expression mode, form parameter characteristic processing technology body, OGPTool provides image conversion feature machining process reasoning rule for parameter characteristic processing technology body simultaneously;
S13, parameter characteristic processing technology body and image conversion feature machining process reasoning rule are passed in Prot é g é modeling tool by data-interface, and in Prot é g é modeling tool, be converted into expression way and the file layout of the support of Prot é g é modeling tool, corresponding generation OWL statistical process ontologies and SWRL process reasoning rule respectively;
S14, OWL statistical process ontologies and SWRL process reasoning rule are passed in Pellet inference machine by plug-in unit, and by Pellet inference machine, OWL statistical process ontologies is carried out the optimization of hierarchical structure and relation according to SWRL process reasoning rule, excavate the relation between potential concept, obtain the OWL feature machining process knowledge ontology of complete optimization, complete the expression of process knowledge.
Further, the OWL process knowledge ontology of described complete optimization is passed in Prot é g é modeling tool by plug-in unit, is then transformed in OGPTool by data-interface and stores as process knowledge.
Further, the specific implementation of step S2 comprises the following steps,
S21, inputs to external process feature in OGPTool, and is converted into the characteristic parameter of OGPTool by OGPTool;
S22, is passed to characteristic parameter in Prot é g é modeling tool by data-interface, and is converted into internal feature example by Prot é g é modeling tool;
S23, SWRL process reasoning rule in internal feature example and Prot é g é modeling tool is combined, and be passed in Pellet inference machine by plug-in unit, and carry out case-based reasoning according to the OWL feature machining technique body of the complete optimization in Pellet inference machine, obtain internal feature job operation example;
S24, is delivered in Prot é g é modeling tool by internal feature job operation example by plug-in unit;
S25, is delivered to the internal feature job operation example in Prot é g é modeling tool in OGPTool by interface, and is converted to characteristic processing method in OGPTool;
S26, derives characteristic processing method from OGPTool, obtains surface job operation tree.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of the device of a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention;
Fig. 2 is the system construction block diagram of the device of a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention;
Fig. 3 is the process flow diagram of the method for a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention;
Fig. 4 is the feature machining process knowledge ontology concept relation graph of the method for a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention;
Fig. 5 is the feature machining process knowledge example sample figure that the present invention invents a kind of method of the feature machining Process Knowledge Representation reasoning based on body;
Fig. 6 is the feature machining process knowledge ontology class based on OGPTool and the relationship modeling schematic diagram thereof of the method for a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention;
Fig. 7 is the parameter process flow diagram of the hole machined process reasoning rule of the method for a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention.
Embodiment
Be described principle of the present invention and feature below in conjunction with accompanying drawing, example, only for explaining the present invention, is not intended to limit scope of the present invention.
As shown in Figure 1, a kind of device of the feature machining Process Knowledge Representation reasoning based on body, comprise the domain body module, graphic parameter metallization processes Ontology Modeling module, general ontology MBM and the reasoning module that are connected successively, be provided with data-interface between described graphic parameter metallization processes Ontology Modeling module and described general ontology MBM, between described general ontology MBM and described reasoning module, be provided with plug-in unit;
Described domain body module, it forms mechanical processing technique domain body for the process knowledge in field of machining being carried out process knowledge ontology modeling;
Described graphic parameter metallization processes Ontology Modeling module, it forms parameter characteristic processing technology body for mechanical processing technique domain body being carried out modeling, and for parameter characteristic processing technology body provide image conversion feature machining process reasoning rule, also for external process feature is converted into characteristic attribute, also for by examples translating for internal feature job operation be characteristic processing method, form surface job operation tree;
Described general ontology MBM, it is converted into general statistical process ontologies and process reasoning rule, also for characteristic attribute is converted into internal feature example for parameter characteristic processing technology body and image conversion feature machining process reasoning being advised correspondence respectively;
Described reasoning module, it is for carrying out the optimization of hierarchical structure and relation according to process reasoning rule by general statistical process ontologies, excavate the relation between potential concept, obtaining the general feature machining process knowledge ontology of complete optimization, also obtaining as internal feature job operation example for internal feature example being carried out case-based reasoning.
Fig. 2 is the system construction block diagram of the device of a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention.As shown in Figure 2, described general ontology MBM is Prot é g é modeling tool, and described reasoning module is Pellet inference machine, and described graphic parameter metallization processes Ontology Modeling module is OGPTool; Described Prot é g é modeling tool and Pellet inference machine all support second edition OWL language and SWRL language, and described second edition OWL language is the language of Expressive Features processing technology ontologies, and described SWRL language is the language describing process knowledge inference rule.Domain body describes the one of disciplinary concept, comprises the constraint of relation between the concept in subject, the attribute of concept, concept and attribute and relation.Because knowledge has significant domain feature, so domain body rationally and effectively can represent knowledge." field " establishes according to the demand of ontological construction person, and it can be an ambit, can be that the one in certain several field combines, also can be in a field one among a small circle.In feature machining process knowledge ontology constructive system, domain body instrument is used for the process knowledge in mechanical processing technique field for data source, feature machining process knowledge ontology is created, concept, attribute, relation, axiom, example, the rule of morphogenesis characters processing technology ontologies according to ontology theory.In order to realize Computerized intelligent working knowledge body, suitable feature machining process knowledge ontology descriptive language is selected to support as computerese.The present invention using OWL2 (second edition of OWL) as feature machining process knowledge ontology descriptive language, using SWRL (SemanticWebRuleLanguage) as process knowledge inference rule descriptive language.OWL is as a kind of language of general process Web information content, and the reading being mainly computer applied algorithm designs, not strong for its readability of the mankind, therefore needs general ontology modeling tool support user to complete OWL Ontology Modeling.The present invention selects to support that the Prot é g é instrument of OWL2 and SWRL is as general ontology modeling, and this instrument provides user oriented Visual Ontology edit tool on the one hand, graphical body can be converted into OWL form; This instrument is as general utility tool on the other hand, can be as integrated in Pellet, FaCT++, Hermit, Racer etc. with most of inference machine.The present invention selects Pellet as rule editor and reasoning tool, realizes optimization and the case-based reasoning of body.Pellet also supports OWL2 and SWRL, and can carry out data conversion with Prot é g é by plug-in unit.Prot é g é is as the general utility tool of Ontology Modeling, and its limitation is that the process of defined notion, relation and rule is too close to language programming pattern, and technological design personnel are difficult to grasp.And process knowledge itself is empirical stronger, contain the hierarchical relationship that " agreement " is good, and inference rule branch is more, extendability requires very high, therefore needs graphic parameter metallization processes ontology modeling tool OGPTool closer to operation layer to complete the modeling of feature machining process knowledge ontology and inference rule.Bottom completes Data Format Transform between OGPTool and Prot é g é by data-interface and concept is corresponding.
Based on the device of above-mentioned a kind of feature machining Process Knowledge Representation reasoning based on body, the present invention also provides a kind of method of the feature machining Process Knowledge Representation reasoning based on body.
As shown in Figure 3, a kind of method of the feature machining Process Knowledge Representation reasoning based on body, comprises the following steps S1 and S2,
S1, expresses the process knowledge in field of machining in the device of a kind of feature machining Process Knowledge Representation reasoning based on body described above, obtains the feature machining process knowledge ontology of expressing.
The specific implementation of step S1 comprises the following steps,
S11, using the process knowledge in mechanical processing technique field as data source, to be characterized as key concept, using ontology as theoretical foundation, carries out process knowledge ontology modeling in domain body module, forms mechanical processing technique domain body;
S12, mechanical processing technique domain body is converted into computer expression mode in OGPTool, and modeling is carried out to the mechanical processing technique domain body of computer expression mode, form parameter characteristic processing technology body, OGPTool provides image conversion feature machining process reasoning rule for parameter characteristic processing technology body simultaneously;
S13, parameter characteristic processing technology body and image conversion feature machining process reasoning rule are passed in Prot é g é modeling tool by data-interface, and in Prot é g é modeling tool, be converted into expression way and the file layout of the support of Prot é g é modeling tool, corresponding generation OWL statistical process ontologies and SWRL process reasoning rule respectively;
S14, OWL statistical process ontologies and SWRL process reasoning rule are passed in Pellet inference machine by plug-in unit, and by Pellet inference machine, OWL statistical process ontologies is carried out the optimization of hierarchical structure and relation according to SWRL process reasoning rule, excavate the relation between potential concept, obtain the OWL feature machining process knowledge ontology of complete optimization, complete the expression of process knowledge.
The OWL process knowledge ontology of described complete optimization is passed in Prot é g é modeling tool by plug-in unit, is then transformed in OGPTool by data-interface and stores as process knowledge.
S2, carries out case-based reasoning by the feature machining process knowledge ontology that external process integrate features is expressed in the device of a kind of feature machining Process Knowledge Representation reasoning based on body described above, obtains surface job operation tree.
The specific implementation of step S2 comprises the following steps,
S21, inputs to external process feature in OGPTool, and is converted into the characteristic parameter of OGPTool by OGPTool;
S22, is passed to characteristic parameter in Prot é g é modeling tool by data-interface, and is converted into internal feature example by Prot é g é modeling tool;
S23, SWRL process reasoning rule in internal feature example and Prot é g é modeling tool is combined, and be passed in Pellet inference machine by plug-in unit, and carry out case-based reasoning according to the OWL feature machining technique body of the complete optimization in Pellet inference machine, obtain internal feature job operation example;
S24, is delivered in Prot é g é modeling tool by internal feature job operation example by plug-in unit;
S25, is delivered to the internal feature job operation example in Prot é g é modeling tool in OGPTool by interface, and is converted to characteristic processing method in OGPTool;
S26, derives characteristic processing method from OGPTool, obtains surface job operation tree.
In the method for a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention, specifically comprise following content:
Feature machining process knowledge ontology based on OWL is expressed:
Based on OWL process knowledge ontology be expressed as four-tuple, i.e. feature machining technique body=(knowledge class, knowledge instance, attribute, relation), what embody is: OFP=(KC, KI, A, R), wherein:
1) KC (knowledge class KnowledgeClass): the set of feature machining process knowledge class (concept), as manufacture feature class (MachiningFeature) and characteristic processing method chain class (FeatureProcessChain) etc.
2) KI (knowledge instance KnowledgeIndividual): the set of feature machining process knowledge example (individuality).In processing technology, each class can have multiple knowledge individual, as
through hole be the example of feature class, the example that rough turn (RoughTurning), half finish turning (SemifinishTurning), finish turning (FinishTurning) they are car (Turning) job operation class, the example etc. that " brill-counterboring-expansion-slightly cut with scissors-finish ream " is characteristic processing method chain class.
3) A (attribute Attribute): certain characteristic being knowledge class, a certain character of reflection knowledge class.In A representation feature processing technology knowledge, the attribute of class and the set of attribute definition, be a class data attribute relation.As hole characteristic class has diameter (hasDiameter), the degree of depth (hasDepth), bottom surface cone angle (hasBottomAngle), whether has the attributes such as preformed hole (hasPreHole).
4) R (relation Relationship): the set of relation between class, individuality in representation feature processing technology knowledge is a class object relation on attributes.This type of relation is divided into two kinds, and a kind of is the hierarchical relationship Rh of representation class, has the relation Rc of technique semanteme between a kind of representation class and individuality.Hierarchical relationship Rh mainly comprises class set membership subClassOf, class brotherhood isSiblingOf, enumerates relation oneof etc. between individual and class.The relation Rc with technique semanteme refers to the process relation between class.As represented the relation hasFeatureProcessChain between manufacture feature class and characteristic processing method chain class.
Fig. 4 is the feature machining process knowledge ontology concept relation graph of the method for a kind of feature machining Process Knowledge Representation reasoning based on body of the present invention, as can be seen from Figure 4, feature machining process knowledge ontology mainly comprises five crucial classes: feature class (MachiningFeature), job operation class (MachiningProcess), characteristic processing method chain class (FeatureProcessChain), characteristic processing method class (FeatureProcess), working ability class (MachiningCapability).
1) feature class (MachiningFeature) refers to the set of manufacture feature class.Feature class as parent, using the subclass of the various characteristic types in front invention as feature class.Feature class comprises the subclass such as hole class (Hole), outside cylinder Noodles (OuterCylinder), is brotherhood between subclass.As parent, feature class gathers around characteristic public attribute, as material properties (hasMaterial), hardness (hasHardness), accuracy class (hasToleranceIT), surfaceness (hasRoughness) etc.As subclass, subcharacter class not only inherits all attributes of parent, but also allow to have the distinctive attribute of subclass self, as hole class has diameter (hasDiameter), the degree of depth (hasDepth), bottom surface cone angle (hasBottomAngle), whether has the attributes such as preformed hole (hasPreHole).
2) job operation class (MachiningProcess) refers to the set of the various job operation classes according to the definition of lathe, cutter and motion morphology, is the basis in process knowledge.Job operation class comprises the subclasses such as boring class (Drilling), boring class (Boring), turning class (Turning), milling class (Milling), is brotherhood between subclass.The subclass of job operation class enumerates class, and all examples namely by listing class are expressed or describe this type of.Job operation is enumerated all processing submethods by the difference of machining precision by the present invention, as turning class comprises the example such as rough turn (RoughTurning), half finish turning (SemifinishTurning), finish turning (FinishTurning), turning class is the combination of all these examples.
3) set of machining feature technological requirement that what characteristic processing method chain class (FeatureProcessChain) was meet, economic job operation sequential combination.Different according to feature subclass, characteristic processing method chain class comprises the subclass such as hole forming method chain (HoleProcessChain), pocket machining method chain (ProcketProcessChain), is brotherhood between subclass.According to the requirement of characteristic processing method reasoning, the attribute of defined feature Machining Methods class: the geometry state (hasPreFeature) before feature machining and physical state (hasPreCondition).
4) characteristic processing method class (FeatureProcess) is to one of the set of job operation class classification and concludes.Classified according to the feature that job operation adapts to, characteristic processing method set as the processing of applicable hole class is hole forming method class (HoleMakingProcess), comprises boring class (Drilling), reaming class (Enlarging), fraising class (Reaming), bore hole class (Boring), car hole class (Turning), hole milling class (Milling) etc.
5) working ability class (MachiningCapability) is the index set of the working ability assessment to job operation and characteristic processing method chain.Often kind of job operation (chain) all has self working ability scope (range), if the material ranges (MaterialRange) of processing, durometer level (HardnessRange), accuracy class scope (ToleranceRange), roughness range (RoughnessRange), range of size (SizeRange) and process redundancy scope (AllowanceRange) etc.
Process relation is a kind of object properties in feature machining technique body is expressed, and the characteristic that object properties have and axiom, process relation also has, as process relation has sub-attribute (hasSubProperty).Between five crucial classes of conceptual level region feature processing technology ontologies, there is following process relation: feature class and characteristic processing method chain exist relation HasFeatureProcessChain, represent that certain feature can reach technological requirement by the processing of certain characteristic processing method chain; There is relation hasMachiningCapability in job operation (chain) class and working ability class, represents the working ability scope of certain job operation (chain); There is relation hasOrderedMachiningProcess in characteristic processing method chain class and job operation class, representation feature Machining Methods is combined by some job operation; There is relation hasMachiningProcess in characteristic processing method class and job operation class, represents that some job operation is applicable to the processing of a certain category feature.
After the structure of feature machining process knowledge ontology and contextual definition are clear and definite, next need to build knowledge instance.Knowledge instance is the method entry in processing technology, have expressed characteristic processing method in detail according to class and relation.If Fig. 5 is feature machining process knowledge example sample, expression be hole category feature example and hole forming method chain example.Certain is characterized as 7 class precisions
hole hole1, surfaceness is 0.8, and material is No. 45 steel, does not have preformed hole (not cast hole) before processing.Suppose that certain characteristic processing method chain is holeprocesschain1, wherein holeprocesschain1hasFirstStepNormalDrilling, hasSecondStepCounterBoring, hasThirdStepRoughReaming, hasFourthStepFinishReaming, the method chain is adapted to have the hole machined as properties: there is no that reservation feature, material are steel, hardness is less than HB400, accuracy class be 7 grades or 8 grades, surfaceness between 0.8 ~ 1.6mm, aperture is between 20 ~ 30; The method chain has 4 steps sequentially, and bore, expand, slightly cut with scissors, finish ream, the range of work often walked is as shown in attribute in Fig. 5.Hole1 and holeprocesschain1 can be obtained by reasoning and there is hasFeatureProcessChain relation, semantically understand from technique, namely the job operation of hole1 can be holeprocesschain1, and according to the diameter value of hole1 and the working ability that often walks, can infer that the process redundancy often walked is as shown in the property value of AR1, AR2, AR3, AR4 in Fig. 5.
When expressing the relation between class, process relation is directly set up when building ontologies, but when expressing the relation between example, the relation between class can be inherited, as the relation hasOrderedMachining in Fig. 5; Part relations is then need reasoning just getable, as set up between example after hasFeatureProcessChain relation characteristics of needs process reasoning; Instance data property value under part relations is also need reasoning just can obtain, as the property value needing surplus reasoning could determine AllowanceRange example under FeatureProcessChain example hasAllowanceRange relation.
Feature process inference rule based on SWRL is expressed:
Expression based on the process knowledge inference rule of SWRL is made up of rules simplify unit, and described regular primitive shape, as function representation, represents function name by class name or relation name, variable with question mark "? " addition of variable name represents.
Feature machining process reasoning is that coupling obtains the job operation meeting feature machining and require from process knowledge.Feature machining process reasoning based on body and SWRL is the property value according to feature class example, and in the example of characteristic processing method chain class, coupling is met the example of rule.Each rule is made up of regular primitive (atom), as MachiningFeature (? f), rule primitive shape is as function representation, function name is represented by class name or relation name, variable with question mark "? " addition of variable name represents, the example of the general representation class of variable or property value.Feature machining process knowledge example sample mesopore processing instance sample according to Fig. 5, the primitive utilizing SWRL to provide expresses hole characteristic process reasoning rule.Rule description as shown in following table table 1,
Table 1
As Hole (? f) represent " if f is an example of Hole class ", this kind of expression is with the example of variable format definition class; And for example hasToleranceIT (? f,? t) accuracy class (ToleranceIT) value of expression f is t, and the attribute of example is expressed in this kind of expression with variable; For another example swrlb:greaterThanOrEuqal (? h,? hu) represent " if expression h >=hu is true ", this type of expression has used the decision logic that the Build-Ins defining variable in SWRL compares.If definition clear-cuts all before symbol "-> ", assignment are effectively and be judged to be true, then can obtain the expression formula after symbol "-> ", as hasFeatureProcessChain (? f;? c), represent to there is hasFeatureProcessChain relation between hole example f and characteristic processing method chain c.During knowledge reasoning, by above-mentioned rule judgment, if there is hasFeatureProcessChain relation between example f and example c, then the characteristic processing method chain of f is c.
Abstract concept, attribute and parameter is only comprised in the regular expression that feature process reasoning uses, the example of feature class and working ability class and attribute replace with variable, therefore, when instance properties value in feature machining process knowledge ontology changes or instance entry needs to expand, its inference rule does not need change.Regular expression is set up for feature, the job operation of often kind of feature can carry out reasoning by a rule, meet between regular example and all can set up hasFeatureProcessChain relation, therefore, multiple characteristic processing method chain can be had by reasoning feature, during actual process design, user is needed to specify or the regular Machining Methods uniquely could determining feature of newly-increased more many condition.
Feature machining technique Ontology Modeling based on OGPTool:
Expression way based on the process knowledge ontology modeling of OPGTool is bulk junction paper mulberry, example, parameter process flow diagram, constraint rule and calculation expression.
OGPTool can express statement type knowledge, control type knowledge and calculation type knowledge respectively.For providing concept and true statement type knowledge, OGPTool is described with bulk junction paper mulberry and example, as characteristic processing method chain knowledge, and the expression etc. of process redundancy; For the knowledge of control type, OGPTool parameter process flow diagram describes, as the expression of feature process inference rule; For the knowledge of calculation type, be described with constraint rule and calculation expression, as the expression that characteristic processing method chain total allowance calculates, machined parameters calculates.
Fig. 6 is that OGPTool carries out feature process ontologies modeling process, concept and the relation of knowledge had been analyzed in " the feature machining process knowledge ontology based on OWL is expressed ", ontologies is set up by same concept and relation at OGPTool, as shown in Figure 6, there is one to one " attribute " relation unlike table and tree node, and be all endowed expression formula and pa-rameter symbols for class and attribute in Fig. 6; Table 2 is certain embodiments table various types of in Fig. 6.
Table 2
Fig. 7 is the parameter process flow diagram of hole machined process reasoning rule, in order to clearly express inference rule, respectively by the pa-rameter symbols used in parameter summary sheet 1 and parameter summary sheet 2 recording parameters flow process and expression formula thereof in Fig. 7.Due in generic attribute modeling process, pa-rameter symbols was designed, then can directly reference parameter symbol and generic attribute relation in parameter Flow Chart Design process.By the judgement branch of logic control pel control law in parameter process flow diagram, the content in pel is judgment rule.
Parameter summary sheet 1
| Parameter name | Expression formula | Pa-rameter symbols |
| Hole class | Hole | ho |
| Material | hasMaterial | m |
| Hardness | hasHardness | h |
| Accuracy class | hasToleranceIT | t |
| Surfaceness | hasRoughness | r |
| Diameter | hasDiameter | d |
| The degree of depth | hasDepth | dp |
| Preformed hole state | hasPreHole | preh |
Parameter summary sheet 2
| Parameter name | Expression formula | Pa-rameter symbols |
| Hole forming method chain class | HoleProcessChain | hc |
| List of materials | hasList | ml |
| The hardness upper limit | hasUpperLimit | hu |
| Hardness lower limit | hasLowerLimit | hl |
| The precision upper limit | hasUpperLimit | tu |
| Precision lower limit | hasLowerLimit | tl |
| The Ra upper limit | hasUpperLimit | ru |
| Ra lower limit | hasLowerLimit | rl |
| Upper dimension bound | hasUpperLimit | su |
| Lower size limit | hasLowerLimit | sl |
| Reservation feature state | hasPreFeature | pref |
Being embodied as of feature machining process knowledge ontology modeling and reasoning:
First process experiences example summarized and conclude, in OGPTool, process knowledge being expressed.The parametrization instrument of OGPTool is utilized to carry out modeling to feature machining process knowledge ontology class, class relation, generic attribute parameter list and inference rule.The explorer of OGPTool is utilized to carry out modeling to feature machining process knowledge ontology example.Then OGPTool converts feature machining process knowledge ontology expression data to XML file form, forms OWL body and expresses and SWRL rule description, be converted to class, object properties, data class attribute, individuality and inference rule respectively after Prot é g é reads.Last Pellet carries out bug check and implication relation reasoning to OWL body.
In Process Planning, first the process attribute that feature identification obtains feature is carried out to part model, then feature and attribute thereof are pushed in OGPTool with Example characteristics form, obtained the job operation of current signature by Parameter Switch and example relation inference.Finally Machining Methods is resolved to feature process, be presented in technological design platform with feature process tree construction.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (9)
1. the device based on the feature machining Process Knowledge Representation reasoning of body, it is characterized in that: comprise the domain body module, graphic parameter metallization processes Ontology Modeling module, general ontology MBM and the reasoning module that are connected successively, be provided with data-interface between described graphic parameter metallization processes Ontology Modeling module and described general ontology MBM, between described general ontology MBM and described reasoning module, be provided with plug-in unit;
Described domain body module, it forms mechanical processing technique domain body for the process knowledge in field of machining being carried out process knowledge ontology modeling;
Described graphic parameter metallization processes Ontology Modeling module, it forms parameter characteristic processing technology body for mechanical processing technique domain body being carried out modeling, and for parameter characteristic processing technology body provide image conversion feature machining process reasoning rule, also for external process feature is converted into characteristic attribute, also for by examples translating for internal feature job operation be characteristic processing method, form surface job operation tree;
Described general ontology MBM, it is converted into general statistical process ontologies and process reasoning rule, also for characteristic attribute is converted into internal feature example for parameter characteristic processing technology body and image conversion feature machining process reasoning being advised correspondence respectively;
Described reasoning module, it is for carrying out the optimization of hierarchical structure and relation according to process reasoning rule by general statistical process ontologies, excavate the relation between potential concept, obtaining the general feature machining process knowledge ontology of complete optimization, also obtaining as internal feature job operation example for internal feature example being carried out case-based reasoning.
2. the device of a kind of feature machining Process Knowledge Representation reasoning based on body according to claim 1, it is characterized in that: described data-interface is used for carrying out Data Format Transform between graphic parameter metallization processes Ontology Modeling module and described general ontology MBM, described plug-in unit is used for carrying out exchanges data between general ontology MBM and reasoning module.
3. the device of a kind of feature machining Process Knowledge Representation reasoning based on body according to claim 1 and 2, it is characterized in that: described general ontology MBM adopts Prot é g é modeling tool, described reasoning module adopts Pellet inference machine, and described graphic parameter metallization processes Ontology Modeling module adopts OGPTool.
4. the device of a kind of feature machining Process Knowledge Representation reasoning based on body according to claim 3, it is characterized in that: described Prot é g é modeling tool and Pellet inference machine all support second edition OWL language and SWRL language, described second edition OWL language is the language of Expressive Features processing technology ontologies, and described SWRL language is the language describing process knowledge inference rule.
5. the device of a kind of feature machining Process Knowledge Representation reasoning based on body according to claim 4, it is characterized in that: based on OWL feature machining process knowledge ontology be expressed as four-tuple, the form of described four-tuple is (knowledge class, knowledge instance, attribute, relation); Expression based on the process knowledge inference rule of SWRL is made up of rules simplify unit, and described regular primitive shape, as function representation, represents function name by class name or relation name, variable with question mark "? " addition of variable name represents; Expression way based on the feature machining process knowledge ontology modeling of OPGTool is bulk junction paper mulberry, example, parameter process flow diagram, constraint rule and calculation expression.
6., based on a method for the feature machining Process Knowledge Representation reasoning of body, it is characterized in that: comprise the following steps,
S1, expresses the process knowledge in field of machining in the device of a kind of feature machining Process Knowledge Representation reasoning based on body described in any one of claim 1 to 5, obtains the feature machining process knowledge ontology of expressing;
S2, carries out case-based reasoning by the feature machining process knowledge ontology that external process integrate features is expressed in the device of a kind of feature machining Process Knowledge Representation reasoning based on body described in any one of claim 1 to 5, obtains surface job operation tree.
7. the method for a kind of feature machining Process Knowledge Representation reasoning based on body according to claim 6, is characterized in that: the specific implementation of step S1 comprises the following steps,
S11, using the process knowledge in mechanical processing technique field as data source, to be characterized as key concept, using ontology as theoretical foundation, carries out process knowledge ontology modeling in domain body module, forms mechanical processing technique domain body;
S12, mechanical processing technique domain body is converted into computer expression mode in OGPTool, and modeling is carried out to the mechanical processing technique domain body of computer expression mode, form parameter characteristic processing technology body, OGPTool provides image conversion feature machining process reasoning rule for parameter characteristic processing technology body simultaneously;
S13, parameter characteristic processing technology body and image conversion feature machining process reasoning rule are passed in Prot é g é modeling tool by data-interface, and in Prot é g é modeling tool, be converted into expression way and the file layout of the support of Prot é g é modeling tool, corresponding generation OWL statistical process ontologies and SWRL process reasoning rule respectively;
S14, OWL statistical process ontologies and SWRL process reasoning rule are passed in Pellet inference machine by plug-in unit, and by Pellet inference machine, OWL statistical process ontologies is carried out the optimization of hierarchical structure and relation according to SWRL process reasoning rule, excavate the relation between potential concept, obtain the OWL feature machining process knowledge ontology of complete optimization, complete the expression of process knowledge.
8. the method for a kind of feature machining Process Knowledge Representation reasoning based on body according to claim 7, it is characterized in that: the OWL process knowledge ontology of described complete optimization is passed in Prot é g é modeling tool by plug-in unit, is then transformed in OGPTool by data-interface and stores as process knowledge.
9. the method for a kind of feature machining Process Knowledge Representation reasoning based on body according to any one of claim 6 to 8, is characterized in that: the specific implementation of step S2 comprises the following steps,
S21, inputs to external process feature in OGPTool, and is converted into the characteristic parameter of OGPTool by OGPTool;
S22, is passed to characteristic parameter in Prot é g é modeling tool by data-interface, and is converted into internal feature example by Prot é g é modeling tool;
S23, SWRL process reasoning rule in internal feature example and Prot é g é modeling tool is combined, and be passed in Pellet inference machine by plug-in unit, and carry out case-based reasoning according to the OWL feature machining technique body of the complete optimization in Pellet inference machine, obtain internal feature job operation example;
S24, is delivered in Prot é g é modeling tool by internal feature job operation example by plug-in unit;
S25, is delivered to the internal feature job operation example in Prot é g é modeling tool in OGPTool by interface, and is converted to characteristic processing method in OGPTool;
S26, derives characteristic processing method from OGPTool, obtains surface job operation tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510713817.8A CN105205537B (en) | 2015-10-28 | 2015-10-28 | A kind of device and method of the feature machining Process Knowledge Representation reasoning based on body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510713817.8A CN105205537B (en) | 2015-10-28 | 2015-10-28 | A kind of device and method of the feature machining Process Knowledge Representation reasoning based on body |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105205537A true CN105205537A (en) | 2015-12-30 |
| CN105205537B CN105205537B (en) | 2017-08-01 |
Family
ID=54953206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510713817.8A Active CN105205537B (en) | 2015-10-28 | 2015-10-28 | A kind of device and method of the feature machining Process Knowledge Representation reasoning based on body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105205537B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704927A (en) * | 2017-09-29 | 2018-02-16 | 西北工业大学 | Skin part detects method of the data to knowledge transformation |
| CN107844573A (en) * | 2017-11-04 | 2018-03-27 | 辽宁工程技术大学 | A kind of input for safety utility analysis method based on production status |
| CN109344454A (en) * | 2018-09-11 | 2019-02-15 | 桂林电子科技大学 | A kind of Benchmark System reasonability self-verifying method based on ontology rule description |
| CN113591964A (en) * | 2021-07-26 | 2021-11-02 | 武汉理工大学 | Simulation knowledge model file format and data fusion system and fusion method |
| CN116680839A (en) * | 2023-08-02 | 2023-09-01 | 长春设备工艺研究所 | Knowledge-driven-based engine intelligent process design method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7096210B1 (en) * | 2000-03-10 | 2006-08-22 | Honeywell International Inc. | Trainable, extensible, automated data-to-knowledge translator |
| US20110191270A1 (en) * | 2010-02-02 | 2011-08-04 | Samsung Electronics Co. Ltd. | Intelligent decision supporting system and method for making intelligent decision |
| CN104199882A (en) * | 2014-08-22 | 2014-12-10 | 北京航空航天大学 | Method for obtaining structural knowledge and ontology of structural knowledge based on intelligent template customization |
| CN104809186A (en) * | 2015-04-20 | 2015-07-29 | 广东工业大学 | Constructing method for mold design and manufacturing knowledge base |
| CN104899242A (en) * | 2015-03-10 | 2015-09-09 | 四川大学 | Mechanical product design two-dimensional knowledge pushing method based on design intent |
-
2015
- 2015-10-28 CN CN201510713817.8A patent/CN105205537B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7096210B1 (en) * | 2000-03-10 | 2006-08-22 | Honeywell International Inc. | Trainable, extensible, automated data-to-knowledge translator |
| US20110191270A1 (en) * | 2010-02-02 | 2011-08-04 | Samsung Electronics Co. Ltd. | Intelligent decision supporting system and method for making intelligent decision |
| CN104199882A (en) * | 2014-08-22 | 2014-12-10 | 北京航空航天大学 | Method for obtaining structural knowledge and ontology of structural knowledge based on intelligent template customization |
| CN104899242A (en) * | 2015-03-10 | 2015-09-09 | 四川大学 | Mechanical product design two-dimensional knowledge pushing method based on design intent |
| CN104809186A (en) * | 2015-04-20 | 2015-07-29 | 广东工业大学 | Constructing method for mold design and manufacturing knowledge base |
Non-Patent Citations (1)
| Title |
|---|
| 孙卫红: "基于知识的网络化制造工艺设计技术及其在机床装备制造中的应用", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704927A (en) * | 2017-09-29 | 2018-02-16 | 西北工业大学 | Skin part detects method of the data to knowledge transformation |
| CN107704927B (en) * | 2017-09-29 | 2021-03-23 | 西北工业大学 | Method for converting skin part detection data into knowledge |
| CN107844573A (en) * | 2017-11-04 | 2018-03-27 | 辽宁工程技术大学 | A kind of input for safety utility analysis method based on production status |
| CN109344454A (en) * | 2018-09-11 | 2019-02-15 | 桂林电子科技大学 | A kind of Benchmark System reasonability self-verifying method based on ontology rule description |
| CN109344454B (en) * | 2018-09-11 | 2023-04-18 | 桂林电子科技大学 | Ontology rule description-based benchmark system rationality automatic inspection method |
| CN113591964A (en) * | 2021-07-26 | 2021-11-02 | 武汉理工大学 | Simulation knowledge model file format and data fusion system and fusion method |
| CN113591964B (en) * | 2021-07-26 | 2024-05-10 | 武汉理工大学 | Data fusion system and method based on simulation knowledge model file |
| CN116680839A (en) * | 2023-08-02 | 2023-09-01 | 长春设备工艺研究所 | Knowledge-driven-based engine intelligent process design method |
| CN116680839B (en) * | 2023-08-02 | 2023-12-08 | 长春设备工艺研究所 | Knowledge-driven-based engine intelligent process design method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105205537B (en) | 2017-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105205537A (en) | Ontology based feature processing technology knowledge representation and inference device and method | |
| Bhandarkar et al. | STEP-based feature extraction from STEP geometry for agile manufacturing | |
| CN101093559B (en) | Method for constructing expert system based on knowledge discovery | |
| Zhou et al. | A feasible approach to the integration of CAD and CAPP | |
| Park | Knowledge capturing methodology in process planning | |
| Chen et al. | A new process knowledge representation approach using parameter flow chart | |
| Liu et al. | Dynamic design method of digital twin process model driven by knowledge-evolution machining features | |
| Equbal et al. | Prediction of dimensional accuracy in fused deposition modelling: a fuzzy logic approach | |
| CN109785180A (en) | A kind of scene perception system and method towards the twin workshop of number | |
| CN104809186B (en) | The construction method of Mould design and manufacturing knowledge base | |
| CN105512258A (en) | Intelligent configuration method for automobile generalized products | |
| Eum et al. | Ontology-based modeling of process selection knowledge for machining feature | |
| Guo et al. | An automatic machining process decision-making system based on knowledge graph | |
| Liu et al. | A semantic feature model in concurrent engineering | |
| Ding et al. | Novel ANN-based feature recognition incorporating design by features | |
| Liu et al. | Dynamic feature modelling for closed-loop machining process control of complex parts | |
| Xu et al. | Machining feature recognition from in-process model of NC simulation | |
| Huang et al. | Multilevel structured NC machining process model based on dynamic machining feature for process reuse | |
| Wang et al. | Machining feature process route planning based on a graph convolutional neural network | |
| CN114254441A (en) | Intelligent generating method of body-based processing method | |
| Zhang et al. | A knowledge reuse-based computer-aided fixture design framework | |
| Huang et al. | An effective numerical control machining process optimization approach of part with complex pockets for numerical control process reuse | |
| Stryczek | A hybrid approach for manufacturability analysis | |
| Hanafy et al. | Integrated products–systems design environment using Bayesian networks | |
| CN116126961B (en) | Tamper-proof unattended weighing data system of regeneration circulation internet of things information system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Ontology based feature processing technology knowledge representation and inference device and method Effective date of registration: 20200624 Granted publication date: 20170801 Pledgee: Industrial Bank Limited by Share Ltd. Wuhan branch Pledgor: WUHAN KM INFORMATION TECHNOLOGY Co.,Ltd. Registration number: Y2020980003478 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230627 Granted publication date: 20170801 Pledgee: Industrial Bank Limited by Share Ltd. Wuhan branch Pledgor: WUHAN KM INFORMATION TECHNOLOGY CO.,LTD. Registration number: Y2020980003478 |