CN108446459A - Process of coking heat consumption influence factor optimization method based on fuzzy semantics reasoning - Google Patents
Process of coking heat consumption influence factor optimization method based on fuzzy semantics reasoning Download PDFInfo
- Publication number
- CN108446459A CN108446459A CN201810170875.4A CN201810170875A CN108446459A CN 108446459 A CN108446459 A CN 108446459A CN 201810170875 A CN201810170875 A CN 201810170875A CN 108446459 A CN108446459 A CN 108446459A
- Authority
- CN
- China
- Prior art keywords
- semantic
- heat consumption
- influence factor
- coking
- semanteme
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to the process of coking heat consumption influence factor optimization methods based on fuzzy semantics reasoning, belong to metallurgical intelligent control, metallurgical automation technology field.The present invention is according to AFS axiom fuzzy set theories, for the influence factor of heat consumption in process of coking, excavate inherent fuzzy semantics, pass through the calculating of semantic evaluation and importance factor, the key for extracting each influence factor is simple semantic, and the parameter area of heat consumption influence factor is set, complete the optimization of process of coking heat consumption influence factor.The present invention optimizes process of coking heat consumption influence factor, and realization ensures to make heat consumption lower target while coke quality qualification in the actual production process.
Description
Technical field
The present invention relates to the process of coking heat consumption influence factor optimization methods based on fuzzy semantics reasoning, belong to metallurgical intelligence
It can control, metallurgical automation technology field.
Background technology
With the development of computer technology and artificial intelligence, fuzzy logic, artificial neural network, evolutionary computation and its integrated
The advanced managements technology such as intelligent model is introduced into each production link of field of metallurgy, metallurgical automatic to realize
Change, intelligent management and control.One of important link as metallurgical production, process of coking include multiple process procedures, each
Link can all generate several technical parameters and data.By taking heat consumption as an example, in the actual production process it is desirable that ensuring coke
Make heat consumption relatively low as possible while charcoal is up-to-standard, to reduce increased production cost production efficiency.However, heat consumption is by numerous
The influence of factor, and there is random and fuzzy uncertainty, therefore we need a kind of effective representation of knowledge and find
Means, accurately to excavate and describe the inherent law and influence factor and consumption of the numerous influence factors of process of coking heat consumption
Relationship between heat, final realize ensure heat consumption lower optimization aim while coke quality qualification.
System based on fuzzy semantics rule can efficiently solve knowledge representation and reasoning problem, pass through fuzzy rule
It indicates knowledge and knowledge is used using fuzzy logic inference.Method based on fuzzy semantics rule can more effectively solve data
Uncertainty more meets reality to the description of data, and analytical performance is higher and should be readily appreciated that.In order to how inquire by observed number
The information contained in is used to determine the membership function of fuzzy concept, and then can use consistent number with fuzzy uncertainty at random
Method is handled, and axiom fuzzy set (Axiomatic Fuzzy Set, AFS) theory is suggested, with imitate human perception and
Observation things then forms concept and generates the mechanism of logic, and fuzzy concept and its logic are discussed from more abstract, general level
Operation.
In view of advantage of the AFS theories in data analysis, in work before, it has been firstly introduced the thought of AFS theories,
Fuzzy semantics expression is carried out to the heat consumption influence factor of process of coking, and therefrom excavates and extracts relevant semantic rules, with
Phase realizes the optimization of heat consumption factor.It is finally by combining expertise to select since the semantic rules quantity excavated is more
Take part of semantic regular, and analysis obtains heat consumption influence factor optimum combination on this basis, tentatively realizes heat consumption
The optimization of factor.However, this process lacks objectivity, there are still certain limitations in practical application, can't reach completely
To the Automatic Optimal of process of coking heat consumption influence factor.
Coking is the significant process in Ferrous Metallurgy production, and the coke quality quality of output directly affects follow-up ironmaking work
The efficiency and quality of skill.And the stable operation and optimum management of coking production process are then to determine coke chemicals quality and technique energy
The key factor of the important indicators such as consumption.In various factors in order to more accurately excavate and describe process of coking heat consumption
In rule, it is further proposed that the relationship in process of coking between various factors and heat consumption, is closed with reaching in coke quality
Ensure heat consumption lower optimization aim while lattice；The present invention proposes a kind of new heat consumption influence factor optimization algorithm.
Invention content
The present invention provides the process of coking heat consumption influence factor optimization methods based on fuzzy semantics reasoning, for solution
The problem of certainly process of coking heat consumption influence factor optimizes, while realization ensures coke quality qualification in the actual production process
Make the lower target of heat consumption.
The present invention uses the thought of AFS theories, by fuzzy semantics come describe a variety of influences of process of coking heat consumption because
The inherent law of element further excavates the relationship in process of coking between various factors and heat consumption, and on this basis
Semantic evaluation function and importance computational methods are defined, and the crucial extraction of semantics for devising heat consumption influence factor is calculated
Method, is finally completed the Automatic Optimal of coking heat consumption influence factor, and realization ensures coke quality qualification in the actual production process
While make the lower target of heat consumption；
In order to reach above-mentioned target, based on the creation data of the practical process of coking of certain large iron and steel enterprise, with consumption
The average value of heat is divided into two higher and relatively low class data samples of heat consumption as boundary, by data, and passes through AFS theories
Excavate the internal relation and rule between the heat consumption and its influence factor of two class samples.The present invention is in existing working foundation
On, it is proposed that a kind of process of coking heat consumption influence factor optimization method based on fuzzy semantics reasoning.
The specific technical solution of the present invention is：Process of coking heat consumption influence factor optimization side based on fuzzy semantics reasoning
Method is excavated inherent fuzzy semantics for the influence factor of heat consumption in process of coking according to AFS axiom fuzzy set theories, is led to
The calculating for crossing semantic evaluation and importance factor, the key for extracting each influence factor is simple semantic, and on heat consumption influence because
The parameter area of element is set, and the optimization of process of coking heat consumption influence factor is completed.
The optimization method is as follows：
Step1, sample data extraction and pretreatment；
The step Step1 the specific steps are：
Step1.1, using the average value of heat consumption as boundary, by data with above and below the average value of heat consumption distinguish
It is divided into two higher and relatively low class data samples of heat consumption；
Step1.2, it is directed to above-mentioned two classes data sample, underlying attribute is retained from initial data；The present invention analyzes coking
The heat consumption influence factor of process, it is research object, including coking time, coal amount (single hole), coke to have chosen 9 underlying attributes
Producer gas main conduit flow, furnace temperature coefficient (coefficient of uniformity), flue gas pusher side suction, flue gas coke side suction, straight trip pusher side temperature,
The moisture for the coke side temperature and coal of keeping straight on；
Step1.3, by the sample space of each attribute by the way of linear transformation by attribute value transform normalization, finally
Constitute sample data sets.
Step2, sample semanteme collection is constructed according to axiom fuzzy set theory；
The step Step2 the specific steps are：
Step2.1, simple semantic expressiveness is carried out to pretreated sample data；
Simple semantic (concept) of the heat consumption major influence factors based on AFS indicates as follows in the present invention：
Assuming that process of coking creation data is N number of sample, each sample chooses 9 influence factors (attribute), then can be used
Matrix X=[the x of one N × 9i,j] indicate all samples, wherein xi,jIndicate j-th of attribute value of the i-th sample.Assuming that M=
{mj,r| 1≤j≤9,1≤r≤6 } it is defined in the simple semantic set on data set X, wherein j=1,2 ..., 9 indicate respectively
J-th of attribute indicate when r=1 " long/big/high ", and when r=2 indicates " non-length/big/high ", and when r=3 indicates " moderate ", when r=4
It indicates " non-moderate ", indicates " short/small/low " when r=5, when r=6 indicates " non-short/small/low ".For any nonvoid subset A of M
In all fuzzy semantics mj,rReferred to as one simple semantic, such as m1,1The simple semanteme indicated is that coking time is long.
The complexity semantic (concept) of the heat consumption major influence factors based on AFS indicates as follows in the present invention：
On the basis of simple semantical definition, to two or more simple semantic progress conjunction or fortune of extracting
It calculates, i.e. logical operation " and " or " or ", you can generate a new fuzzy semantics, an also referred to as complex concept or multiple
Miscellaneous semanteme.Such as A1=m1,1and m9,3It can indicate " moisture of coking time length and coal is moderate "；A2=m2,5and m4,1It can
It indicates " coal amount is small and coefficient of uniformity is big "；A3=A1+A2, you can indicate " moisture of coking time length and coal is moderate, or
Person's coal amount is small and coefficient of uniformity is big ", also referred to as " m1,1m9,3+m2,5m4,1”。
Step2.2, structure semantic weight function；
Step2.3, structure fuzzy semantics membership function；
(1) simple semantic degree
The semantic concept for portraying some sample is defined according to the distribution of the specific object value of data sample, is led to
Simple semantic degree is crossed to embody.Vacation lets f be the fuzzy semantics set on data set X, forX ∈ X, Aτ(x) it is sample
X belongs to the degree of A, indicates as follows：
Wherein, mj,rA simple concept in gathering for F,Indicate that sample x belongs to concept mj,rDegree it is small
Belong to m in or equal to sample yj,rDegree, i.e. Aτ(x) it is to meetThe set of all sample y of condition, is sample X
A subset.
(2) semantic weight function
(3) fuzzy semantics membership function (i.e. AFS membership functions)
Arbitrary fuzzy conceptMembership function, provided according to following formula：
Wherein, NuIndicate that the observation frequency of sample, S are the number of A.μα(x) i.e. can be described as sample x belongs to being subordinate to for concept α
Degree.
Step2.4, the degree of membership that sample belongs to each simple semanteme is calculated by membership function, and according to this degree of membership
With simple semantic screening threshold value, the simple semantic collection of coking heat consumption is extracted；
Step2.5, collected according to simple semanteme, construction is complicated semantic, belongs to each multiple by membership function calculating sample
The degree of membership of miscellaneous semanteme, and according to this degree of membership and complicated semantic screening threshold value, extract the semantic collection of complexity of coking heat consumption.
According to the simple semantic collection of sample xIt is calculated by the membership function of formula (2) each complicated semanticDegree of membershipSetting screening threshold value σ2, extract the semantic set of complexity of coking heat consumption
Assuming that sample data X is divided into C classes, then CkClass semantic rules collection is：
WhereinFor CkThe number of samples of class.
Step3, semantic evaluation and importance factor calculating are carried out；
(1), semantic evaluation
Define evaluation function ω (Av) semanteme is collectedIn semantic AvIt is evaluated, specific formula for calculation is as follows：
WhereinFor CkThe number of samples of class, PiIndicate semanteme AvTo sample xiContribution degree, ω (Av) indicate semanteme Av
To the contribution degree degree of consistency of all samples, consistency more high evaluation value is bigger, and the contribution degree of the semanteme is bigger.
(2), the calculating of semantic importance factor
Define semantic importance factorCalculate semantic collectionIn semantic AvImportance, calculation formula is as follows：
Wherein,It indicatesSimple semanteme m in semanteme setj,rThe number of appearance,It indicatesSemanteme collection
All simple semantic number summations occurred in conjunction,It indicatesSimple semanteme m in semanteme setj,rThe frequency of appearance.
Step4, the key of extraction process of coking heat consumption influence factor are simple semantic；
According to semantic AvImportanceIt is ranked up from big to small, constructs new semantic setSuccessively fromChoosing
Take the higher semanteme A of semantic importancev, traverse AvIn all simple semanteme mj,r, a key of each attribute is extracted successively
It is simple semantic, and constitute crucial simple semantic set Km。
Step5, the parameter area for setting process of coking heat consumption influence factor realize process of coking heat consumption influence factor
Optimization；Wherein, it for each sample attribute, sorts according to its attribute value size, after finding out sequence according to AFS membership functions
Each sample is distributed according to the degree of membership of calculated all samples for its simple semantic degree of membership and then determines parameter
Setting range.
Assuming that CkIt is represented as the relatively low class of heat consumption, KmIn contain 9 keys simply semanteme mj,r, wherein each heat consumption
Influence factor corresponds to a simple semanteme.By CkAll samples of class are ranked up according to the size of attribute j, and according to formula (2)
All samples are calculated successively belongs to semantic mj,rDegree of membership distribution, and then determine the m of attribute jj,rSemantic value range is realized
Process of coking heat consumption influence factor optimizes.
The key that 9 main heat consumption influence factors are extracted in the present invention is semantic, to obtain coke oven control in process of coking
The value range of parameter processed.But the method for the present invention is not limited only to the optimization of 9 listed heat consumption factors, also can be to reality
The influence factor of other keys optimizes in production.
The beneficial effects of the invention are as follows：
The present invention optimizes process of coking heat consumption influence factor, and realization ensures that coke quality closes in the actual production process
Make heat consumption lower target while lattice, with the increase of creation data, available one group of the method for the present invention more suits reality
Border production requirement and more comprehensively accurate heat consumption factors optimization parameter, the informationization to the actual production of coke making process and intelligence
Energyization provides decision support.
Description of the drawings
Fig. 1 is triangle weighting function；
Fig. 2 is AFS membership functions.
Specific implementation mode
Embodiment 1：As shown in Figs. 1-2, the process of coking heat consumption influence factor optimization method based on fuzzy semantics reasoning,
The present embodiment is by taking 150 in coking production process true generation data (sample) as an example, and the specific steps of the optimization method are such as
Under：
Step1, sample data extraction and pretreatment；
Step1.1, calculate 150 samples heat consumption mean value, and sample is divided into the relatively low class of heat consumption according to mean value
C1(being less than mean value) and the higher class C of heat consumption2(being more than or equal to mean value) two class data, number of samples is respectively 80 and 70；
Step1.2, for every data in two classes, 9 underlying attributes (factor) are only retained from initial data, respectively
For coking time, coal amount (single hole), coke-stove gas main conduit flow, furnace temperature coefficient (coefficient of uniformity), flue gas pusher side suction, cigarette
The moisture of road gas coke side suction, straight trip pusher side temperature, the coke side temperature and coal of keeping straight on, is denoted as f1, f2..., f9；
Step1.3, by the sample space of each attribute by the way of linear transformation by attribute value(i-th sample
J-th of attribute value) transform normalization to [0,1] section,To keep number
According to probability distribution.Sample data sets X is finally constituted, sample set X is then the matrix of a 150*9.
Step2, sample semanteme collection is constructed according to axiom fuzzy set theory；
Step2.1, simple semantic expressiveness is carried out to pretreated sample data；Enable M={ mj,r|1≤j≤9,1≤r≤
6 } the simple semantic collection being defined on data set X, it is corresponding semantic as shown in table 1, i.e. it is simple semantic comprising 54 in M；
Table 1
Step2.2, semantic weight function is set as trigonometric function, as shown in Figure 1, nodal value is respectively set to 0.2,0.5,
0.8.Wherein ρ1,ρ2,ρ3Respectively " short/small/low ", " moderate ", " long/big/high " three semantic weighting functions.Assuming that sample x
Value on some attribute is 0.5, then the weights that the sample belongs to semantic " short/small/low " are 0, belongs to " moderate " semanteme
Weight is 1, and it is 0 to belong to " long/big/high " semantic weight.Its " non-short/small/low ", " non-moderate ", " non-length/big/high " three
Semantic weight is respectively 1-0,1-0.5,1-0；
Step2.3, structure fuzzy semantics membership function；Its function is as follows：
Wherein, NuIndicate that the observation frequency of sample, S are the number of A, μα(x) i.e. can be described as sample x belongs to being subordinate to for concept α
Degree；
The simple semantic screening threshold value σ of Step2.4, setting screening coking heat consumption factor1=0.8, for the every of every class
A sample calculates separately sample x using membership function formula (2) and belongs to each simple semanteme mj,rDegree of membershipIt carries
Take satisfactionThe simple semantic simple semantic collection for constituting sample x
The semantic screening threshold value σ of complexity of Step2.5, setting screening coking heat consumption factor2=0.75, for each sample
X, construction it is all fromThe middle simple semantic complexity generated by " and " for choosing 2 or 2 or more (length is not more than 4)
Semantic Av, the degree of membership of public formula (2) calculating of profitExtraction meetsComplexity it is semantic, constitute sample x
The semantic set of complexityThe quantity of the fuzzy semantics collection of extraction and threshold value σ1、σ2, set semantic concept length is most
Big value and sample size and property distribution are related.
Step2.6, the complexity semanteme by all samples of each classBy extracting, operation is attached, respectively structure
Make the semantic set of two classesWith
Step3, semantic evaluation and importance factor calculating are carried out；
Ensure to make heat consumption lower target while coke quality qualification in the actual production process in order to realize, I
Only the semantic rules set of the relatively low class of heat consumption is analyzed.By above-mentioned Step1+Step2 steps, heat consumption can be obtained
Relatively low semantic setThe one group of complex concept extracted by 44 semantic concepts (rule) and formed, length 2,3 and 4
Semanteme has 14,21 and 9 respectively.These semantemes are evaluated below, and calculate importance factor：
Step3.1, semantic evaluation；Utilization assessment functionIt calculates
In 44 semanteme AvEvaluation of estimate ω (Av)；
Wherein,For CkThe number of samples of class, PiIndicate semanteme AvTo sample xiContribution degree, ω (Av) indicate semanteme Av
To the contribution degree degree of consistency of all samples；
The calculating of Step3.2, semantic importance factor；StatisticsIn 44 semantemes in each simple semanteme mj,rGo out
Existing times Nj,r, calculate separately each simple semantic frequency occurredCalculate each semanteme AvThe institute of middle appearance
There is the sum of the frequency of simple concept
Step3.3, pass through formulaTo calculate each semanteme AvImportance factor
Wherein, It indicatesSimple semanteme m in semanteme setj,r
The number of appearance,It indicatesAll simple semantic number summations occurred in semanteme set,It indicatesIt is semantic
Simple semanteme m in setj,rThe frequency of appearance.
Step4, the key of extraction process of coking heat consumption influence factor are simple semantic；
Step4.1, according to semantic importance factorSemanteme is ranked up according to sequence from big to small, is constructed
New semantic setAnd initialize crucial simple semantic set
Step4.2, fromIn successively from semanteme A of high importancevMiddle all simple semanteme m of traversalj,rIfAnd1≤q≤6, while r is odd number (non-semantic), then by the simple semanteme mj,rIt is added to set Km
In.In short, only choosing a crucial simple semanteme to each attribute；
Step4.3, step Step4.2 is repeated, until KmKey of the set comprising all properties is simple semantic；
Step4.4, through the above steps, obtains m successively6,5, m2,5, m5,3, m4,1, m8,3, m9,5, m7,3, m1,3, m3,5Deng 9
The set K of the simple semantic composition of factorm。
Step5, the parameter area for setting process of coking heat consumption influence factor complete process of coking heat consumption influence factor
Optimization.
Set KmMiddle m1,3, m2,5, m3,5, m4,1, m5,3, m6,5, m7,3, m8,3, m9,5The semanteme of expression is respectively：Coking time
It is moderate, coal amount (single hole) is small, coke-stove gas main conduit flow is small, furnace temperature coefficient (coefficient of uniformity) is high, flue gas pusher side suction is suitable
In, flue gas coke side suction is small, straight trip pusher side moderate temperature, straight trip coke side moderate temperature, the moisture of coal are small.In other words, it to reach
To ensuring to make while coke quality qualification the lower target of heat consumption in actual production process it is necessary to consuming in making above 9
The parameter value of heat factor is controlled as possible in corresponding semantic coverage.We are semantic by above key below, further really
The parameter setting range of fixed each factor.
Step5.1, it is directed to each attribute, with coal amount f2For, by all samples according to the big of coal amount attribute value
It is small to be ranked up, each sample after sequence is found out for semantic m further according to formula (2) (AFS membership functions)2,1(coal amount
Greatly), m2,3(coal amount is moderate), m2,5(coal amount is small) three semantic degrees of membership, mf3, mf2 and mf1 as shown in Figure 2.
As can be seen from Figure 2, the actual attribute distribution structure membership function of AFS theoretical foundations feature, rather than it is subjective fixed
Adopted membership function, to avoid the inaccuracy generated by Subjective difference.The semanteme built by the membership function
Logic rules operation can be carried out, characteristic attribute can be more fully portrayed.
Step5.2, set KmThe coal amount f extracted2The semantic key of attribute is m2,5, then its interval can be set
It is set toWhereinHere value indicates the desirable of attribute value
Value meetsI.e. attribute value v belongs to semantic m2,5Be subordinate to
Degree, which is more than, belongs to other semantic degrees of membership.In fig. 2 it is possible to be interpreted as,0 is should be,For the friendship of function mf1 and mf2
The value of the corresponding abscissa of point.
Step5.3, due to attribute value pretreatment when be normalized, utilize following formula willWithValue mapping
To the original value range of attribute, coal amount f can be obtained2The value lower limit of attributeAnd the upper limit
Step5.4, according to Step5.1 to Step5.3, can equally obtain the value upper and lower bound of other attributes, point
It is not denoted asWithWherein j=1,2 ..., 9.It can be obtained coke oven Optimization about control parameter tables of data and parameter in process of coking
Setting range, as shown in table 2.
Table 2
The specific implementation mode of the present invention is explained in detail above in conjunction with attached drawing, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
Put that various changes can be made.
Claims (9)
1. the process of coking heat consumption influence factor optimization method based on fuzzy semantics reasoning, it is characterised in that：According to AFS axioms
Fuzzy set theory excavates inherent fuzzy semantics for the influence factor of heat consumption in process of coking, by semantic evaluation and
The calculating of importance factor, the key for extracting each influence factor is simple semantic, and to the parameter area of heat consumption influence factor into
The optimization of process of coking heat consumption influence factor is completed in row setting.
2. the process of coking heat consumption influence factor optimization method according to claim 1 based on fuzzy semantics reasoning,
It is characterized in that：The optimization method is as follows：
Step1, sample data extraction and pretreatment；
Step2, sample semanteme collection is constructed according to axiom fuzzy set theory；
Step3, semantic evaluation and importance factor calculating are carried out；
Step4, the key of extraction process of coking heat consumption influence factor are simple semantic；
It is excellent to complete process of coking heat consumption influence factor for Step5, the parameter area for setting process of coking heat consumption influence factor
Change.
3. the process of coking heat consumption influence factor optimization method according to claim 2 based on fuzzy semantics reasoning,
It is characterized in that：The step Step1 the specific steps are：
Step1.1, using the average value of heat consumption as boundary, data are respectively divided with the average value above and below heat consumption
For the two class data samples that heat consumption is higher and relatively low；
Step1.2, it is directed to above-mentioned two classes data sample, underlying attribute is retained from initial data；Including coking time, coal
Amount, coke-stove gas main conduit flow, furnace temperature coefficient, flue gas pusher side suction, flue gas coke side suction, straight trip pusher side temperature, straight trip
The moisture of coke side temperature and coal；
Step1.3, by the sample space of each attribute by the way of linear transformation by attribute value transform normalization, finally constitute
Sample data sets.
4. the process of coking heat consumption influence factor optimization method according to claim 2 based on fuzzy semantics reasoning,
It is characterized in that：The step Step2 the specific steps are：
Step2.1, simple semantic expressiveness is carried out to pretreated sample data；
Step2.2, structure semantic weight function；
Step2.3, structure fuzzy semantics membership function；
Step2.4, the degree of membership that sample belongs to each simple semanteme is calculated by membership function, and according to this degree of membership and letter
Single semantic screening threshold value extracts the simple semantic collection of coking heat consumption；
Step2.5, collected according to simple semanteme, construction is complicated semantic, belongs to each complicated language by membership function calculating sample
The degree of membership of justice, and according to this degree of membership and complicated semantic screening threshold value, extract the semantic collection of complexity of coking heat consumption.
5. the process of coking heat consumption influence factor optimization method according to claim 4 based on fuzzy semantics reasoning,
It is characterized in that：The simple semantic screening threshold value is 0.8, and complicated semantic screening threshold value is 0.75；
Extraction meets simple semantic degree of membership and is more than or equal to the simple semantic simple semantic letter for constituting sample for screening threshold value 0.8
Single semantic collection；
Extraction meets complicated semantic degree of membership and constitutes sample more than or equal to the complicated semantic complexity semanteme for screening threshold value 0.75
Complicated semantic collection.
6. the process of coking heat consumption influence factor optimization method according to claim 2 based on fuzzy semantics reasoning,
It is characterized in that：In the step Step3, Utilization assessment functionPass through analytic language
Justice evaluates semanteme all sample contribution degree degree of consistency；
Wherein,For CkThe number of samples of class, PiIndicate semanteme AvTo sample xiContribution degree, ω (Av) indicate semanteme AvTo institute
There is the contribution degree degree of consistency of sample.
7. the process of coking heat consumption influence factor optimization method according to claim 6 based on fuzzy semantics reasoning,
It is characterized in that：In the step Step3, the frequency occurred is concentrated semantic by semantic evaluation and simple semanteme, passes through public affairs
FormulaTo calculate the importance factor of each semanteme；
Wherein, It indicatesSimple semanteme m in semanteme setj,rOccur
Number,It indicatesAll simple semantic number summations occurred in semanteme set,It indicatesSemanteme set
In simple semanteme mj,rThe frequency of appearance.
8. the process of coking heat consumption influence factor optimization method according to claim 2 based on fuzzy semantics reasoning,
It is characterized in that：In the step Step4, according to the size of the semantic importance factor, successively from the high semanteme of importance factor
Extraction is crucial simple semantic.
9. the process of coking heat consumption influence factor optimization method according to claim 2 based on fuzzy semantics reasoning,
It is characterized in that：In the step Step5, for each sample attribute, sort according to its attribute value size, according to AFS degrees of membership
Function finds out each sample after sequence for its simple semantic degree of membership, and according to the degree of membership of calculated all samples
It is distributed and then determines parameter setting range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810170875.4A CN108446459B (en) | 2018-03-01 | 2018-03-01 | Fuzzy semantic reasoning-based coking process heat consumption influence factor optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810170875.4A CN108446459B (en) | 2018-03-01 | 2018-03-01 | Fuzzy semantic reasoning-based coking process heat consumption influence factor optimization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108446459A true CN108446459A (en) | 2018-08-24 |
| CN108446459B CN108446459B (en) | 2022-03-22 |
Family
ID=63193253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810170875.4A Active CN108446459B (en) | 2018-03-01 | 2018-03-01 | Fuzzy semantic reasoning-based coking process heat consumption influence factor optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108446459B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1435781A (en) * | 2003-02-24 | 2003-08-13 | 杨炳儒 | Intelligent decision supporting configuration method based on information excavation |
| US20040243419A1 (en) * | 2003-05-29 | 2004-12-02 | Microsoft Corporation | Semantic object synchronous understanding for highly interactive interface |
| CN101674328A (en) * | 2009-11-18 | 2010-03-17 | 南京理工大学 | Subject service describing and matching method based on semantic and QoS constraint |
| CN102636991A (en) * | 2012-04-18 | 2012-08-15 | 国电科学技术研究院 | Method for optimizing running parameters of thermal power unit and based on fuzzy set association rule |
| CN102663122A (en) * | 2012-04-20 | 2012-09-12 | 北京邮电大学 | Semantic query expansion algorithm based on emergency ontology |
| US20140161354A1 (en) * | 2012-12-06 | 2014-06-12 | Nokia Corporation | Method and apparatus for semantic extraction and video remix creation |
| CN104763999A (en) * | 2015-03-04 | 2015-07-08 | 内蒙古瑞特优化科技股份有限公司 | Power plant pulverized coal boiler combustion performance online optimizing method and system |
-
2018
- 2018-03-01 CN CN201810170875.4A patent/CN108446459B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1435781A (en) * | 2003-02-24 | 2003-08-13 | 杨炳儒 | Intelligent decision supporting configuration method based on information excavation |
| US20040243419A1 (en) * | 2003-05-29 | 2004-12-02 | Microsoft Corporation | Semantic object synchronous understanding for highly interactive interface |
| CN101674328A (en) * | 2009-11-18 | 2010-03-17 | 南京理工大学 | Subject service describing and matching method based on semantic and QoS constraint |
| CN102636991A (en) * | 2012-04-18 | 2012-08-15 | 国电科学技术研究院 | Method for optimizing running parameters of thermal power unit and based on fuzzy set association rule |
| CN102663122A (en) * | 2012-04-20 | 2012-09-12 | 北京邮电大学 | Semantic query expansion algorithm based on emergency ontology |
| US20140161354A1 (en) * | 2012-12-06 | 2014-06-12 | Nokia Corporation | Method and apparatus for semantic extraction and video remix creation |
| CN104763999A (en) * | 2015-03-04 | 2015-07-08 | 内蒙古瑞特优化科技股份有限公司 | Power plant pulverized coal boiler combustion performance online optimizing method and system |
Non-Patent Citations (2)
| Title |
|---|
| 甘健侯等: "基于本体与物联网的冶金炼焦过程语义化及建模应用研究", 《中国博士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 郭锐等: "基于模糊贡献度的水面舰艇作战模糊推理方法", 《火力与指挥控制》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108446459B (en) | 2022-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Adeleke et al. | Prediction of municipal solid waste generation: an investigation of the effect of clustering techniques and parameters on ANFIS model performance | |
| Alrashidi et al. | Metaheuristic optimization algorithms to estimate statistical distribution parameters for characterizing wind speeds | |
| Dariane et al. | Forecasting streamflow by combination of a genetic input selection algorithm and wavelet transforms using ANFIS models | |
| Jiang et al. | Prediction of ecological pressure on resource-based cities based on an RBF neural network optimized by an improved ABC algorithm | |
| CN108304978A (en) | A kind of mid-term Electric Power Load Forecast method based on data clusters theory | |
| CN105931116A (en) | Automated credit scoring system and method based on depth learning mechanism | |
| Zhu et al. | Coke price prediction approach based on dense GRU and opposition-based learning salp swarm algorithm | |
| CN106529732A (en) | Carbon emission efficiency prediction method based on neural network and random frontier analysis | |
| Khan et al. | Evaluating the performance of several data mining methods for predicting irrigation water requirement | |
| CN107871183A (en) | Permafrost Area highway distress Forecasting Methodology based on uncertain Clouds theory | |
| Kayhomayoon et al. | A new approach for regional groundwater level simulation: clustering, simulation, and optimization | |
| Zhou et al. | Comprehensive evaluation of land reclamation and utilisation schemes based on a modified VIKOR method for surface mines | |
| Emami | Seasons optimization algorithm | |
| CN115376008A (en) | Method and device for identifying plant diseases and insect pests, electronic equipment and storage medium | |
| Mahalakshmi et al. | Mamdani fuzzy rule based model to classify sites for aquaculture development | |
| CN110458722A (en) | Flood interval prediction method based on multiple target random vector function connection network | |
| CN117314266B (en) | Novel intelligent scientific and technological talent evaluation method based on hypergraph attention mechanism | |
| CN115994459B (en) | Method, system and equipment for optimizing construction time sequence of mass power grid infrastructure projects | |
| Wang et al. | Spatial Co-location Pattern Mining Based on Fuzzy Neighbor Relationship. | |
| Hashemy et al. | Facilitation of operation and maintenance activities of irrigation networks using ak‐means clustering method: case study of the ghazvin irrigation network | |
| CN108446459A (en) | Process of coking heat consumption influence factor optimization method based on fuzzy semantics reasoning | |
| CN109886454A (en) | A kind of fresh water environment wawter bloom prediction technique based on self-organizing deepness belief network and Method Using Relevance Vector Machine | |
| Guo et al. | The back propagation based on the modified group method of data-handling network for oilfield production forecasting | |
| Lu et al. | A deep belief network based model for urban haze prediction | |
| CN108493933A (en) | A kind of Characteristics of Electric Load method for digging based on depth decision Tree algorithms |
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 |