CN107247810B - Method for constructing knowledge base system based on device operation of styrene chemical process - Google Patents
Method for constructing knowledge base system based on device operation of styrene chemical process Download PDFInfo
- Publication number
- CN107247810B CN107247810B CN201710597844.2A CN201710597844A CN107247810B CN 107247810 B CN107247810 B CN 107247810B CN 201710597844 A CN201710597844 A CN 201710597844A CN 107247810 B CN107247810 B CN 107247810B
- Authority
- CN
- China
- Prior art keywords
- instance
- chemical process
- constructing
- ontology
- styrene
- 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.)
- Active
Links
- PPBRXRYQALVLMV-UHFFFAOYSA-N Styrene Chemical compound C=CC1=CC=CC=C1 PPBRXRYQALVLMV-UHFFFAOYSA-N 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001311 chemical methods and process Methods 0.000 title claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- YNQLUTRBYVCPMQ-UHFFFAOYSA-N Ethylbenzene Chemical compound CCC1=CC=CC=C1 YNQLUTRBYVCPMQ-UHFFFAOYSA-N 0.000 claims description 32
- 238000005804 alkylation reaction Methods 0.000 claims description 11
- 239000000126 substance Substances 0.000 claims description 9
- 238000005265 energy consumption Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 7
- 238000010992 reflux Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000006356 dehydrogenation reaction Methods 0.000 claims description 2
- 230000000295 complement effect Effects 0.000 claims 1
- 239000013589 supplement Substances 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 abstract description 2
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 description 6
- 230000029936 alkylation Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 235000006719 Cassia obtusifolia Nutrition 0.000 description 3
- 235000014552 Cassia tora Nutrition 0.000 description 3
- 244000201986 Cassia tora Species 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 description 2
- 239000005977 Ethylene Substances 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Crystallography & Structural Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for constructing a knowledge base system based on device operation of a styrene chemical process, which comprises the following steps: a) Constructing an ontology describing operations involved in a styrene chemical process; b) Constructing a rule base, wherein the rule base is used for carrying out consistency test and supplement perfection on the body; c) Analyzing the body to obtain information after the body analysis; d) And storing the information to obtain the knowledge base system.
Description
Technical Field
The invention relates to the field of chemical industry, in particular to a method for constructing a knowledge base system based on device operation of a styrene chemical process.
Background
The knowledge base system is aimed at the problem of specific field, adopts a certain knowledge expression mode to make storage, organization and inquiry of mutually-related knowledge piece set in computer.
The ontology is a tool for describing concepts and interrelationships among the concepts, and by establishing a concept model and defining hierarchical relations among the concepts, the abstraction, structuring and systemization of knowledge are realized, so that based on the characteristics of the ontology, the ontology technology is one of important technologies for constructing a knowledge base system.
Ontologies have received much attention since they were applied to the engineering field, and many studies have been conducted on ontologies in the engineering field, but most of them are frames for proposing modeling methods for ontologies, and are not specific to a specific part. The ontology construction research in the chemical industry field is relatively few, and is mainly focused on ontology modeling in the petrochemical industry field, so that the ontology construction research on the aspect of the operation of the chemical device is very few, and the knowledge reuse and sharing on the aspect of the operation of the chemical device are not facilitated.
Disclosure of Invention
The invention provides a method for constructing a knowledge base system for device operation based on a styrene chemical process, which can be used for retrieving the operation of a corresponding device according to a production target.
In accordance with the above objects, the present invention provides a method of constructing a knowledge base system for device operation based on a styrene chemical process, the method comprising: a) Constructing an ontology describing operations involved in a styrene chemical process; b) Constructing a rule base, wherein the rule base is used for carrying out consistency test and supplement perfection on the body; c) Analyzing the body to obtain information after the body analysis; d) And storing the information to obtain the knowledge base system.
In an embodiment, the method further comprises: and constructing a knowledge retrieval layer to provide a basis for retrieving the conditions of the device operation based on the information, wherein the rule base further comprises rules required by the retrieving operation so as to obtain the conditions of the device operation.
In an embodiment, a knowledge retrieval layer is constructed to provide a basis for retrieving conditions under which the device operates based on the information, wherein the rule base includes rules that are required in order to obtain the conditions when retrieving.
In an embodiment, the method further comprises: and constructing an interface layer for receiving the user instruction and displaying the retrieved condition of the device operation.
In one embodiment, the interface layer is built using the MVC framework of JSP+JavaBean+Serverlet.
In an embodiment, the step a) further comprises: determining the domain and scope of an ontology, considering multiplexing existing ontologies, listing important terms in the ontology, defining classes and hierarchical relationships of the classes, defining attributes, defining attribute facets, and creating instances.
In one embodiment, the step of defining the class includes: classes are defined according to a set of concepts involved in the styrene chemistry.
In one embodiment, the step of defining the attribute includes: and determining the relation among concepts according to the concept set related to the styrene chemical process so as to complete the step of defining the attribute.
In one embodiment, the instances include a device instance, a model instance, a range of operating conditions instance, an optimal operating conditions instance, a variable instance, and an operation instance.
In an embodiment, the step d) further comprises: and executing the stored operation by adopting a Mysql database.
In one embodiment, the rule base is constructed in the rule description language SWRL and Java language.
In one embodiment, the parsing is performed using a Jena API written in Java language.
In one embodiment, the device of the styrene chemical process comprises an alkylation reaction unit, an ethylbenzene rectification unit, an ethylbenzene dehydrogenation unit and a styrene rectification unit.
In one embodiment, the operations of building the ontology include applying the principles of complex event handling to abstract up the operations involved in the styrene chemical process.
The invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of any of the preceding when executing the program.
The present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of any of the preceding.
In summary, the method for constructing the knowledge base system based on the device operation of the styrene chemical process utilizes the related principles of the ontology to establish the knowledge base, and the established knowledge base is utilized to search the optimal working condition which accords with the production target.
Drawings
FIG. 1 illustrates a flow chart of one aspect of a method of constructing a knowledge base system for device operation based on a styrene chemical process of the present invention;
FIG. 2 shows a flow chart of a designed decision tree algorithm;
FIG. 3 illustrates an example of selecting an optimal operating condition using an established knowledge base.
Detailed Description
The invention provides a method for constructing a knowledge base system for device operation based on a styrene chemical process, which can be used for retrieving the operation of a corresponding device according to a production target.
Referring to FIG. 1, FIG. 1 illustrates a flow chart of one aspect of a method of constructing a knowledge base system for device operation based on a styrene chemical process of the present invention, the method comprising:
step 101: constructing a body;
step 102: constructing a rule base;
step 103: analyzing the body to obtain information after body analysis;
step 104: information is stored to obtain a knowledge base system.
Step 101 is then performed first to build the ontology, i.e. to create an ontology layer.
The ontology is mainly based on a styrene chemical process and is used for describing operations in the process and relations between the operations.
The ontology is completed by adopting a seven-step method of an ontology classical construction method, wherein the seven-step method comprises the following steps: determining the domain and scope of the ontology, considering multiplexing the existing ontology, listing important terms in the ontology, defining class and class hierarchical relationship, defining attribute facets, and creating an instance. Wherein definition of class layer, definition of attribute layer and creation of instance layer are core steps in the ontology construction process.
A class refers to a collection of objects having the same characteristics or the same attributes, and is typically defined by a framework, including the name of the class and its natural language description. And classifying according to the concept set involved in the styrene chemical process, thereby completing definition of class layers of the ontology.
Attributes are used to describe the relationships between classes or classes and data, so attributes in turn include object attributes and data attributes. And determining the relation among concepts according to the concept set related to the styrene chemical process, thereby completing the definition of the ontology attribute layer.
An instance belongs to a class, owns all the attributes that the class has, and is a specific description and concrete representation of the class. The instance layer therefore needs to be built by means of class layers.
The ontology can be built by means of the Prot ontology building software, for example, when a class layer is built, the default top class in the Prot ontology building software is the Thing class, and seven top classes of chemical equipment class "chemical equipment", operation class "Event", optimal working condition class "optimal Condition", working condition class "Condition Range", operation Variable class "Variable" and Model "are built under the Thing class respectively.
Wherein, the chemical equipment refers to equipment related to the styrene chemical process, for example, an alkylation reactor; events are abstractions of device operations, defining events to correspond to operations; operation refers to operations involved in the styrene chemical process, such as an increase in the alkylation reactor inlet temperature; the working condition refers to a specific working condition range of the chemical device; the optimal working condition depends on a working condition range, and refers to the optimal operation working condition in a specific working condition range; operating variables, i.e., those involved in the styrene chemical process; the models, namely the models applicable to the working condition and the optimal working condition, are different in general models, and the working condition range and the optimal working condition are also different.
Defining seven top-level classes should be disjoint, i.e. an instance cannot belong to some of the seven classes. On the basis of determining seven top-level classes, subdividing the top-level classes downward, taking the operation as an example, the operation defined to the next level is as follows: temperature operation, flow operation, pressure operation, reflux ratio operation, etc.
For the styrene chemical process, when an attribute layer is established, the established object attributes mainly comprise cause, coCause, happenAfter, happenBefore, happenMeanwhile, fitCondition, fitEquipment, fitModel, hasOptiMumCondition, hasvariableCondition and the like. The first five of which correspond to the operating conditions, equipment, models, most useful operating conditions, and operating variables, respectively, for the event class.
The established data attributes mainly include hasFlow, hasPressure, hasTemperature, hasRefluxRatio and hasSolutionRatio and other attributes directly related to specific numerical values, and FlowRange, pressureRange, temperatureRange, refluxRatioRange, solutionRatioRange and other attributes with sub-attribute representing range values.
Tables 1 and 2 show the fields and values of some object properties and some data properties, respectively.
TABLE 1 definition fields and value fields for some object properties
| Object Property | Domain | Range | Comment |
| Cause | Event | Event | One event causing another event |
| FitCondition | ChemicalEquipment | WorkingCondition | Which condition the device satisfies |
| FitEquipment | WorkingCondition | ChemicalEquipment | Working condition of which equipment |
| FitModel | WorkingCondition | Model | Which model is satisfied |
| HasVariableCondition | WorkingCondition | Variable | What variables are involved |
| HasOptimumCondition | WorkingCondition | OptimumCondition | Corresponding optimal working condition |
TABLE 2 definition fields and value fields for some data attributes
| Object Property | Domain | Range | Comment |
| HasFlow | Variable | Float | Flow rate |
| HasRefluxRatio | Variable | Float | Reflux ratio |
| HasPressure | Variable | Float | Pressure of |
| HasTemperature | Variable | Float | Temperature (temperature) |
| HasSolutionRatio | Variable | Variable | Water ratio |
| Increase | Operation | Boolean | Increasing operation |
| Decease | Operation | Boolean | Reducing operation |
In one embodiment, the operation of building an ontology includes applying principles of complex event processing.
The construction of the ontology introduces the concept of Complex Event Processing (CEP), which abstracts up a series of operations involved in the styrene chemical process, causes corresponding events by the change of the operation variables, and takes corresponding operations by the events.
When an instance layer is created, the instance mainly comprises six categories, namely an equipment instance, a model instance, a working condition range instance, an optimal working condition instance, a variable instance and an operation instance, wherein the working condition range instance is taken as a center, and the rest of the instances are connected with the instance through attributes.
The built ontology describes the operation level of the styrene chemical process, namely the relation between the operation variables and the operations of the device. Examples of the alkylation reactor of the alkylation reaction unit include reactor inlet temperature, benzene feed rate, ethylene feed rate, reflux ratio, etc., and examples of the operation include increasing (decreasing) temperature, increasing (decreasing) feed rate, etc.
Step 102, creating a rule base. The rule base is a rule set established for the ontology, and has the functions of carrying out implicit reasoning on the ontology, exploring the implicit knowledge of the ontology, expanding and perfecting the information expressed by the ontology, enabling the original ontology to describe more complex relations, and carrying out logical reasoning according to the retrieval conditions input by the interface layer to obtain a result conforming to the retrieval conditions. The former is mainly used for perfecting the ontology in a broader sense, and the latter is used for reasoning the ontology according to specific conditions.
In one embodiment, the writing of rules is implemented using the rule description language SWRL.
In one embodiment, the reasoning of the ontology is implemented using a Pellet reasoning engine.
If the Rule is added under the Rule Tab page in the Prot < g > under the Prot < g > software environment. Based on event processing, device operations in the styrene chemical process are abstracted, so that rules added by the rule base are mainly aimed at event processing.
An exemplary rule is as follows:
ReactionInletMaterialTCE(？x),ProductionChangeEvent(？y),isExothermicReact ion(？x,true),isIncreased(？x,true),cause(？x,？y)->isDecreased(？y,true)
the meaning of this rule is: an x event is an example of a reactor inlet feed temperature event and a y event is an example of a production event, if the x event causes the y event to occur and the reaction is an exothermic reaction, then an increase in the temperature of the inlet feed will correspondingly result in a decrease in production.
The corresponding rule can be extracted by processing real-time data in the production process and simulation data generated by Aspen software modeling.
Through the continuous accumulation and processing of the data and simulation data of the actual chemical process, new rules can be added to the rule base continuously, and existing rules in the rule base can be adjusted and perfected.
Step 103 and step 104 are to create an analysis layer, where the purpose of the analysis layer is to analyze the ontology constructed in the ontology layer, and then store the information obtained by analysis in a database, so that the analysis layer includes two steps, namely, analysis of the ontology and storage of the ontology.
In one embodiment, the parsing of the ontology employs a Jena API written in Java language, which provides not only the corresponding classes and methods for reading the classes, attributes and instances in the ontology, but also some classes and methods for reasoning of the ontology.
The parsing step includes modeling, reading the ontology file, obtaining classes in the ontology, obtaining instances in the ontology and instance attributes. The classes used are mainly ModelMaker, model, ontModel; the method mainly comprises getModelMaker, createOntology, modellistClasses, istAllOntProperties, listIndividuals.
In one embodiment, the body is stored by using a Mysql relational database, which specifically comprises two steps of database table structure design and storage, wherein the database table structure design is completed according to information of body description and query logic of implementation, and the storage is realized by using JDBC.
The ontology is stored by using a Mysql relational database, and a table structure is required to be designed. In one example, the adopted tabulation strategy is as follows: firstly, building a resource table which contains all information of the built body, including classes, attributes, examples, relation constraints among the classes, the attributes, the examples and the like; then, separately building a list for each class, namely a class list, a property list and an index list for the three classes class, property and the index. The classification is clear and visual, the inquiry is facilitated, and the excessive forms are prevented from being bloated. In addition to the four tables, a table is needed to store the attribute of the instance, i.e., indivCon table. In the class table, the included fields are ClassId, className, type and superClassName, the primary bond is ClassId, and the self-growth is performed; in the property table, the contained fields are PropId, propName, type, domain, roles, and the primary key is Propid, which is self-growing; in the index table, the fields are IndivId, indivName, type, className, classId, indivId for the primary key, classId for the outer key, and thus the class table and the index table are associated. In the indivicon table, the fields included are IndivName, prop, propValue, indivId, propId, and the foreign keys are IndivId and PropId, so that the indivcon table is associated with the indivical and property tables.
In an embodiment, the method further comprises constructing a knowledge retrieval layer to provide a basis for retrieving conditions under which the device operates based on the information, wherein the rule base comprises rules required in retrieving in order to obtain the conditions.
The knowledge retrieval layer aims to quickly and accurately inquire the most conforming retrieval result by adopting a corresponding algorithm according to the retrieval conditions input by the interface layer.
In an embodiment, the knowledge retrieval layer includes a decision tree algorithm for retrieving conditions of operation of the device based on the information in response to a retrieval instruction by a user.
The decision tree algorithm constructs different branches by splitting the attributes until a node meeting the requirements is obtained or a stop condition is reached. Taking an alkylation reaction unit as an example, the splitting attribute can be selected from ethylbenzene precision, ethylbenzene yield, energy consumption of unit product and the like.
The choice of attribute splitting depends on the optimization objective to be achieved. In one example, taking an alkylation unit of a styrene chemical process as an example, the objectives that generally need to be optimized include ethylbenzene yield, ethylbenzene accuracy, plant energy consumption, etc., and the priority of the optimization objectives is accuracy > yield > energy consumption. Three optimization objectives are assigned a weight, w1=0.5, w2=0.3 and w3=0.2, respectively. Defining the inquired ethylbenzene precision a1, the target precision is a2, the inquired ethylbenzene yield b1, the target yield b2, the inquired device energy consumption c1 and the target energy consumption c2, and defining S as follows:
S＝S 1 ×S 2 ×S 3 ＝(a 1 -a 2 )×w 1 +(b 1 -b 2 )×w 2 +(c 1 -c 2 )×w 3
and calculating S, and judging the most suitable result according to the size of the S.
Referring to fig. 2, fig. 2 shows a flow chart of a designed decision tree algorithm, comprising:
step 201: and judging that the input actual working condition is in a specific working condition range of the model, if the corresponding working condition range is not found, turning to step 207, otherwise turning to step 202.
Step 202: and inquiring the optimal working condition corresponding to the working condition range.
Step 203: if ethylbenzene precision a1> optimizes target a2, s1= (a 1-a 2) ×w1, go to Step4; if not, go to step 207.
Step 204: if ethylbenzene yield b1> optimizes target b2, s2= (b 1-b 2) ×w2, go to Step5; if not, go to step 207.
Step 205: if the device energy consumption c1 is less than the optimization target c2, s3= (c 2-c 1) ×w3, and Step6 is performed; if not, go to step 207.
Step 206: s=s1×s2×s3 is calculated, and the most suitable result is selected according to the order of the sizes.
Step 207: and (3) the optimization operation meeting the conditions is not obtained, and the optimization operation fails.
In an embodiment, the method further comprises constructing an interface layer for receiving user instructions and displaying retrieved conditions for operation of the device.
The interface layer is used for receiving user input and displaying knowledge retrieval results. The user inputs the search condition according to the self requirement on the front page, the background queries the database, and the result which is most in line with the search condition is returned to the front page according to the corresponding rule and the decision tree algorithm.
In one embodiment, the interface layer is built using the MVC framework of JSP+JavaBean+Serverlet. Wherein Servlet represents a Controller portion in the MVC framework, jsp represents a View portion in the MVC framework, and JavaBean represents a Model portion in the MVC framework.
Referring to FIG. 3 for an alkylation reaction unit for a styrene flow scheme, FIG. 3 shows an example of selecting optimal conditions using an established knowledge base, comprising:
step 301: inputting the current reaction working conditions, including the actual working conditions such as the inlet temperature of an alkylation reactor, the feeding flow of benzene, the feeding flow of ethylene, the reflux ratio of the alkylation reactor and the like;
step 302: inputting targets to be optimized, including ethylbenzene yield, ethylbenzene precision and device energy consumption;
step 303: system output: the optimal working condition most accords with the input condition of the user.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A method of constructing a knowledge base system for device operation based on a styrene chemical process, the method comprising:
constructing a body with pressure operation, temperature operation, flow operation and reflux ratio operation of the device, the body describing operations involved in a styrene chemical process;
creating an instance, wherein the instance comprises a device instance, a model instance, a working condition range instance, an optimal working condition instance, a variable instance and an operation instance, and each instance is centered on the working condition range instance and is connected with the working condition range instance through an attribute;
constructing a rule base comprising rules required for retrieving operating conditions of the device, for consistency checking and complement refinement of the body, and for exploring implicit knowledge of the pressure operation, the temperature operation, the flow operation, and the reflux ratio operation;
analyzing the body to obtain information after the body analysis;
storing the information to obtain the knowledge base system; and
and constructing a knowledge retrieval layer, wherein the knowledge retrieval layer comprises a decision tree algorithm, and the decision tree algorithm responds to a retrieval instruction of a user and performs attribute division retrieval on the operation conditions of the device according to the ethylbenzene yield, the ethylbenzene precision and the optimization target of the device energy consumption and the preset priority weight so as to determine the optimization operation conforming to the operation conditions.
2. The method of claim 1, wherein the step of building a body with pressure operation, temperature operation, flow operation, and reflux ratio operation of the device comprises:
determining the domain and range of the ontology;
multiplexing the existing body;
listing important terms in the ontology;
defining class and class grade relation; and
attributes and attribute facets are defined.
3. The method of claim 2, wherein the step of defining the class comprises:
the classes are defined according to a set of concepts involved in the styrene chemical process.
4. The method of claim 2, wherein the step of defining the attribute comprises:
and determining the relation between concepts according to the concept set related to the styrene chemical process.
5. The method of claim 1, wherein the styrene chemical plant comprises an alkylation reaction unit, an ethylbenzene rectification unit, an ethylbenzene dehydrogenation unit, and a styrene rectification unit.
6. The method of claim 1, wherein constructing the ontology comprises abstracting operations involved in the styrene chemical process upward using principles of complex event handling.
7. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements a method of constructing a knowledge base system for device operation based on a styrene chemical process as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710597844.2A CN107247810B (en) | 2017-07-20 | 2017-07-20 | Method for constructing knowledge base system based on device operation of styrene chemical process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710597844.2A CN107247810B (en) | 2017-07-20 | 2017-07-20 | Method for constructing knowledge base system based on device operation of styrene chemical process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107247810A CN107247810A (en) | 2017-10-13 |
| CN107247810B true CN107247810B (en) | 2023-12-19 |
Family
ID=60013994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710597844.2A Active CN107247810B (en) | 2017-07-20 | 2017-07-20 | Method for constructing knowledge base system based on device operation of styrene chemical process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107247810B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184489A (en) * | 2011-05-27 | 2011-09-14 | 苏州两江科技有限公司 | Knowledge-based workflow management system |
| CN106204317A (en) * | 2016-07-12 | 2016-12-07 | 桂林电子科技大学 | Subassembly detection method based on body |
-
2017
- 2017-07-20 CN CN201710597844.2A patent/CN107247810B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184489A (en) * | 2011-05-27 | 2011-09-14 | 苏州两江科技有限公司 | Knowledge-based workflow management system |
| CN106204317A (en) * | 2016-07-12 | 2016-12-07 | 桂林电子科技大学 | Subassembly detection method based on body |
Non-Patent Citations (6)
| Title |
|---|
| 基于本体的农产品电子标签复杂事件处理引擎;朱华吉 等;《农业工程学报》;20080930;第24卷;25、39 * |
| 基于本体的电子病历知识库研究;要芳;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20090815;156 * |
| 工业生产中的知识自动化决策***;陈晓方，吴仁超，桂卫华;《中兴通讯技术》;20161031;第22卷(第5期);43 * |
| 朱华吉 等.基于本体的农产品电子标签复杂事件处理引擎.《农业工程学报》.2008,第24卷156-160. * |
| 石油化工知识管理方法探讨;刘卫东;《中国管理信息化》;20150228;第18卷(第3期);76 * |
| 要芳.基于本体的电子病历知识库研究.《中国优秀硕士学位论文全文数据库医药卫生科技辑》.2009,25-39. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107247810A (en) | 2017-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | A novel knowledge graph-based optimization approach for resource allocation in discrete manufacturing workshops | |
| Gong et al. | Neo4j graph database realizes efficient storage performance of oilfield ontology | |
| Dao et al. | A declarative framework for constrained clustering | |
| CN104699698A (en) | Graph query processing method based on massive data | |
| CN110110402B (en) | Binary decision diagram-based method for quickly solving reachable state of resource distribution system | |
| Koehler et al. | Logical foundations of possibilistic keys | |
| US9020954B2 (en) | Ranking supervised hashing | |
| Qiao et al. | A 3D assembly model retrieval method based on assembly information | |
| Zhang et al. | Knowledge representation framework combining case-based reasoning with knowledge graphs for product design | |
| CN115757810A (en) | Method for constructing standard ontology of knowledge graph | |
| Zhao et al. | An ontology self-learning approach for CNC machine capability information integration and representation in cloud manufacturing | |
| Bao et al. | A node2vec-based graph embedding approach for unified assembly process information modeling and workstep execution time prediction | |
| Sreenivasula Reddy et al. | Intuitionistic fuzzy rough sets and fruit fly algorithm for association rule mining | |
| Hong et al. | Ontological modelling of knowledge management for human-machine integrated design of ultra-precision grinding machine | |
| Kalifullah et al. | Retracted: Graph‐based content matching for web of things through heuristic boost algorithm | |
| Sharma et al. | Indexer++ workload-aware online index tuning with transformers and reinforcement learning | |
| CN109086381A (en) | A kind of update generation method of Fuzzy Concept Lattice | |
| Fan et al. | Integrating multi-granularity model and similarity measurement for transforming process data into different granularity knowledge | |
| CN107247810B (en) | Method for constructing knowledge base system based on device operation of styrene chemical process | |
| CN106649551A (en) | Retrieval method based on CBR finite element template | |
| CN110352417A (en) | Ontological construction auxiliary device | |
| CN107436919B (en) | Cloud manufacturing standard service modeling method based on ontology and BOSS | |
| CN110232184A (en) | The machining service two-way semantic matching method of supply and demand under a kind of cloud manufacturing mode | |
| Lei et al. | Hybrid knowledge model of process planning and its green extension | |
| CN102270190B (en) | Computer modeling and solving processing method of complex decision-making problem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |