CN102799151A - Statistical-classification-based method for real-time balance adjustment of metallurgical gas system - Google Patents

Abstract

The invention relates to a statistical-classification-based method for the real-time balance adjustment of a metallurgical gas system. The method is characterized by comprising the following steps of: firstly separating moments corresponding to adjusting unit data into adjusting moments and non-adjusting moments by applying a Gaussian process classifier, taking generating unit data, consumption unit data and adjusted unit data, which correspond to the adjusting moments, as samples of a fuzzy rule base, and establishing an adjusting sample base; then converting all samples in the sample base into If-Then fuzzy rules by using a fuzzy C-mean clustering algorithm, and establishing a complete fuzzy rule base; when the condition that the gas system is about to be in unbalanced operation at some moment is monitored, converting gas generating unit data and consumption unit data at the moment into the If-Then fuzzy rules by using the fuzzy C-mean clustering algorithm, comparing with the established fuzzy rule base, and determining adjustable units at the moment; obtaining the total adjustment quantity of the gas system by adopting a differential calculation method; and finally allocating the total adjustment quantity to different adjusting units according to the priority levels of the adjusting units and the maximum load capacity of each adjusting unit of the gas system, thereby realizing the real-time balance adjustment of the metallurgical gas system.

Description

A kind of real-time balance adjustment method of metallurgical coal gas system based on statistical classification

Technical field

The invention belongs to areas of information technology, relate to Gaussian process, fuzzy rule base and Difference Calculation, is a kind of real-time balance adjustment method of metallurgical coal gas system based on statistical classification.The present invention utilizes the on-the-spot existing mass data of smelter; At first use the Gaussian process grader adjustment unit data moment corresponding is separated into the adjustment moment and the non-adjustment moment; The generating unit data that adjustment is constantly corresponding, consumable unit data and by the sample of adjustment unit as fuzzy rule base are set up adjustment sample storehouse; Use the fuzzy C-means clustering algorithm will adjust the fuzzy rule that each sample conversion in the sample storehouse becomes If-Then then, set up complete fuzzy rule base; Be about to the operation imbalance when monitoring a certain moment of coal gas system; Use the fuzzy C-means clustering algorithm to convert the fuzzy rule of If-Then to the coal gas generating unit data and the consumable unit data in this moment; Compare with the fuzzy rule base of being set up, but determine the adjustment unit in this moment; Adopt the Difference Calculation method to obtain the adjustment total amount of coal gas system then; Based on the priority of coal gas system adjustment unit and the peak load ability of each adjustment unit, the adjustment total amount is distributed to different adjustment units at last, realize the real-time balance adjustment of metallurgical coal gas system.

Background technology

The energy is the most important resource except that human resources in the smelter production run, and whether the ruuning situation of energy resource system stable, economical, reliably will directly have influence on the quality and the economic benefit of enterprises of product.Therefore, the by-product gas that how efficiently to utilize production run to produce makes enterprise's low consumption, low diffusing; Low cost, the low pollution moved target (Jun Zhao, the Quanli Liu that becomes the smelter pursuit; Wei Wang, Witold Pedrycz, and Liqun Cong; Hybrid Neural Prediction and Optimized Adjustment for Coke Oven Gas System in Steel Industry [J] .IEEE trans.on neural networks and learning systems., vol.23, no.3; Pp.439-450, Mar.2012).

The smelter production run can produce a large amount of by-product gas; And this type of secondary product also is the available important secondary energy of link such as coking, heating furnace, power plant, thermal treatment, and its effective and reasonable utilization will directly have influence on the energy consumption standard and the output cost of smelter.By-product gas comprises three kinds of coke-oven gas, blast furnace gas and coal gas of converter.Because the non-regularity of Iron and Steel Production, the unbalanced situation that disappears takes place to produce through regular meeting in coal gas system, produces with the too much or very few cabinet position of very easily causing of surplus that consumes to exceed the upper limit or lower limit, influences security of system, therefore must adjust effectively coal gas.Generally speaking; When the cabinet position of gas chamber takes place when unusual; According to the variation tendency that coal gas system produces the unit that disappears, the gas using quantity that increases or reduce adjustable unit in the pipe network can balance gas chamber position, the most important thing is under the prerequisite that guarantees ordinary production and gas chamber safe operation, to maximize the utilization factor of coal gas; Reduce the amount of diffusing of by-product gas, reduce production costs.

In actual production process, the dispatcher often relies on artificial experience to realize the balance adjustment to whole coal gas system at present.With reference to on-the-spot actual conditions; The dispatcher generally estimates whether needs adjustment according to the product of each unit in the practical operation situation of current time cabinet position and the system quantitative changeization that disappears; And the rough adjustment total amount that calculates; To adjust total amount according to artificial experience then and distribute to different adjustment units; If the running status of adjustment back coal gas system reaches the requirement of expection then stops adjustment; Otherwise will constantly adjust, till meeting the demands.The weak point of this method is that the dispatcher need accomplish huge workload; Though can provide the adjustment total amount, can not provide concrete adjustment scheme directly and accurately, the adjustment mode of this dependence artificial experience needs adjustment constantly; This can cause the hysteresis of adjustment means response; Can't accomplish the balance adjustment of coal gas system timely and effectively, also possibly cause the improper production of enterprise, influence the productivity effect of enterprise.

Summary of the invention

The technical matters that the present invention will solve is the real-time balance adjustment of a metallurgical coal gas system problem.For addressing the above problem; At first using the Gaussian process sorter will adjust constantly corresponding adjustment unit data and separate with the corresponding constantly adjustment unit data of non-adjustment; The generating unit data that adjustment is constantly corresponding, consumable unit data and by the sample of adjustment unit as fuzzy rule base; Set up adjustment sample storehouse, set up fuzzy rule base, be used for confirming adjustment unit based on this adjustment sample storehouse; Obtain coal gas adjustment total amount through the Difference Calculation method then; At last, will adjust total amount and distribute to different adjustment units according to the priority of the coal gas system adjustment unit at scene and the peak load ability of each adjustment unit.Utilize this invention can provide adjustment scheme preferably within a short period of time and supply dispatcher's reference, realize the balance adjustment of metallurgical coal gas system.

The whole realization flow of technical scheme of the present invention is shown in accompanying drawing 1, and concrete steps are following:

1, reading of field data: from metallurgical coal gas system for field real-time data base, read required coal gas system adjustment unit data, by adjustment unit, generating unit data, consumable unit data, gas-holder location data;

2, Gaussian process two disaggregated models: employing Gaussian process sorter is separated into the adjustment unit data moment corresponding that obtains in the 1st step and adjusts constantly and the non-adjustment moment, and record adjustment corresponding adjustment unit data of the moment;

3, set up fuzzy rule base: the generating unit data that the adjustment that obtains in the 2nd step is corresponding constantly and the data of consumable unit are as the input sample of fuzzy rule base; With adjustment constantly corresponding by the output sample of adjustment unit as fuzzy rule base; Set up adjustment sample storehouse; Utilize the fuzzy C-means clustering algorithm will adjust the fuzzy rule that each sample in the sample storehouse converts If-Then to, set up comparatively complete fuzzy rule base;

4, real-time online is confirmed adjustment unit: the monitoring coal gas system moves the unbalanced moment; Generating unit data and consumable unit data that this is corresponding constantly; Use the fuzzy C-means clustering algorithm to convert the fuzzy rule of If-Then to; Compare with the fuzzy rule base that the 3rd step was set up; Find out with fuzzy rule base in the most close fuzzy rule, but its output is exactly the adjustment unit of current time;

5, the calculating of adjustment total amount: adopt the acquisition of Difference Calculation method to need the coal gas total amount of adjustment;

6, the adjustment amount that distributes each adjustment unit:,, the adjustment total amount that the 5th step obtained is distributed to different adjustment units according to the priority of on-the-spot adjustment unit and the peak load ability of each adjustment unit according to the adjustment unit that obtains in the 4th step.

Effect of the present invention and benefit are:

Consider that the spot dispatch personnel rely on artificial experience to confirm the blindness of adjustment unit; The present invention adopts the method real-time online that combines based on Gaussian process sorter and fuzzy rule base to confirm adjustment unit; Can effectively avoid the dependence of system, and improve the speed of definite adjustment unit effectively, solve the problem that adjustment lags behind artificial experience; Realize the reasonable utilization and the distribution of coal gas, thereby realize industrial robotization and intelligent operation;

The present invention makes full use of the on-the-spot existing field data of smelter; The real-time and precise whole unit of setting the tone really; And after adopting the Difference Calculation method to obtain the adjustment total amount,, will adjust total amount and distribute to different adjustment units according to the priority of adjustment unit and the peak load ability of each adjustment unit; Satisfy on-site real-time property and stability requirement, thereby complete feasible adjustment scheme is provided for the dispatcher of coal gas system.

Description of drawings

Fig. 1 is the whole realization flow figure of technical scheme.

Fig. 2 is smelter coal gas system pipe network structure figure.

Fig. 3 is the adjustment total schematic diagram of coal gas system.

Embodiment

In order to understand technical scheme of the present invention better; Describe in detail below in conjunction with 2 pairs of embodiments of the present invention of accompanying drawing; Accompanying drawing 2 is the pipe network structure figure of certain smelter coal gas system; Blast furnace, coke oven and converter are the generating units of coal gas system, the blast furnace gas of its generation, coke-oven gas and coal gas of converter through the pressurizing point pressurization after, supply with consumable unit such as limekiln, sintering plant, continuous casting, cold rolling, hot rolling, pipe mill, breaking down and use; Coal gas more than needed can supply with low-pressure boiler and boiler of power plant produces steam and electric power; But low-pressure boiler and boiler of power plant are the adjustment units of coal gas system, are the important adjustment means that can guarantee system balancing in coal gas system, and the pipe network of coal gas system is the memory device of coal gas system with the gas chamber that links to each other with gaspipe network in addition.Generally; Coal gas system can remain on the disappear state operation of balance of a product, sometimes because industrial change or industrial failure and other reasons can cause the imbalance of coal gas system, when drug on the market; The cabinet position of gas chamber possibly surpass its operation upper limit; To open in this case and diffuse tower and diffuse unnecessary coal gas, when supply falls short of demand, may cause industrial stagnation.So monitoring abnormal conditions will take place the time, needing in time adjust, so that coal gas system reaches new balance to coal gas system.The dispatcher of present on-the-spot coal gas system is through monitor the running status of coal gas system in real time; Judge whether coal gas system will need adjustment constantly in future, and under the situation of needs adjustment, rough calculation goes out to adjust total amount; Confirm adjustment unit according to artificial experience then; But so not only workload is very big, and depends on dispatcher's experience, causes the hysteresis of adjusting easily; So the present invention proposes a kind of real-time balance adjustment method of metallurgical coal gas system based on statistical classification, realize that metallurgical coal gas system is analyzed automatically, control and adjustment automatically automatically.According to method flow shown in Figure 1, practical implementation step of the present invention is following:

Step 1: the reading of field data

From smelter on-site real-time database read required coal gas system adjustment unit data, by adjustment unit classification, generating unit data, consumable unit data, gas-holder location data.

In order to narrate conveniently; Provide adjustment implication constantly earlier: in some minutes; If the gas chamber position is in higher or during low state always; The consumption of any adjustment unit suddenlys change suddenly, explains that this adjustment unit carries out the balance adjustment to coal gas system, claims that then this catastrophe point moment corresponding is the adjustment moment.For adjustment characteristic constantly, applicant of the present invention draws coal gas system after the field staff with the Shanghai Baosteel Energy Center links up adjustment possesses following characteristic constantly:

(1) the gas chamber position is being in higher or lower state for a long time always, if do not adjust, probably transfiniting in following a period of time in the gas chamber position, influences the security of system.

(2) if having the consumption of one or several adjustment units to suddenly change suddenly this moment, coal gas system is carried out the balance adjustment, make the gas chamber position be tending towards normal gradually from plateau.

Generally speaking,, then can increase the consumption of adjustment unit suddenly,, then can reduce the consumption of adjustment unit suddenly,, guarantee that system normally moves in order to coal gas system is carried out the balance adjustment when the gas chamber position is in low state when the gas chamber position is in higher state.

Step 2: set up Gaussian process two disaggregated models

Read known adjustment unit data and form a sample set; The slope of the point that the interval in each sample in the calculating sample set is identical; With the input sample of resulting all slope value as Gaussian process two disaggregated models; Output sample is each input sample corresponding class label, the data of input sample and output sample

Sample set is expressed as D={ (x _i, y _i) | _{I=1 ..., N}, wherein import sample x _i∈ R ^d, output sample y _i∈ 1,1}, y _i=1 this sample moment corresponding of expression is the adjustment moment, y _i=-1 this sample moment corresponding of expression is the non-adjustment moment, and N is the number of input sample.

At given input sample x _iSituation under, be to calculate output sample y _i, introduce implicit function f, make f _i=f (x _i), then all the implicit function values with implicit function are designated as f=[f ₁, f ₂..., f _N] ^TKnown output sample y _iWith each implicit function value f _iBetween have following dependence p (y _i| f _i)=Φ (y _if _i), and each output sample y _iSeparate, the joint likelihood function of output sample can be described as so:

$p\left(y\right|f)=\underset{i=1}{\overset{N}{\mathrm{\Π}}}p\left(y_i\right|f_i)=\underset{i=1}{\overset{N}{\mathrm{\Π}}}\mathrm{\Φ}\left(y_i{f}_i\right)---\left(1\right)$

Given ultra parameter θ, according to bayesian criterion, the posteriority distribution table of implicit function value f is shown:

$p\left(f\right|D,\mathrm{\θ})=\frac{p\left(y\right|f)p\left(f\right|X,\mathrm{\θ})}{p\left(D\right|\mathrm{\θ})}=\frac{N\left(f\right|0,K)}{p\left(D\right|\mathrm{\θ})}\underset{i=1}{\overset{N}{\mathrm{\Π}}}\mathrm{\Φ}\left(y_i{f}_i\right)---\left(2\right)$

Wherein, X is the input sample set, is designated as X=[x ₁..., x _N]; Suppose each implicit function value f _iPrior distribution be the zero-mean Gaussian distribution, so given input sample set X, the joint distribution of implicit function value should be obeyed polynary Gaussian distribution, promptly p (f|X, θ)=N (f|0, K); K is the covariance matrix of implicit function value f, and each element definition among the K is K _Ij=K (x _i, x _j, θ), K is the covariance function of positive definite.Given detection sample x _*, desire to ask its implicit function value f _*Posterior probability distribute, can distribute to the posteriority of the implicit function value f in the formula (2) and carry out marginalisation, f so _*Posteriority distribute and can be expressed as:

p(f _*|D，θ，x _*)＝∫p(f _*|f，X，θ，x _*)p(f|D，θ)df (3)

In the posteriority distribution substitution formula (3) with the implicit function value f in the formula (2), draw approximate posterior probability

$q\left(f_{*}\right|D,\mathrm{\θ},x_{*})=N\left(f_{*}\right|{\mathrm{\μ}}_{*},{\mathrm{\σ}}_{*}^2)---\left(4\right)$

Average and variance are respectively:

${\mathrm{\μ}}_{*}=k_{*}^T{K}^{-1}m,{\mathrm{\σ}}_{*}^2=K(x_{*},x_{*})-k_{*}^T(K^{-1}-K^{-1}{\mathrm{AK}}^{-1})k_{*}---\left(5\right)$

Here k _*Be to detect sample x _*With the covariance of input sample set X, k _*=[K (x ₁, x _*) ..., K (x _N, x _*)] ^TM and A are the average and the variances of implicit function value f Gaussian distributed, with q (f|D, the APPROXIMATE DISTRIBUTION that θ) implicit function value f is obeyed during expression set of data samples D, satisfy q (f|D, θ)=N (f|m, A).According to formula (4) and expectation computing formula, given detection sample x _*, output sample y then _*The approximate value that belongs to the probability of classification 1 can be expressed as:

$q(y_{*}=1|D,\mathrm{\θ},x_{*})=\∫\mathrm{\Φ}\left(f_{*}\right)N\left(f_{*}\right|{\mathrm{\μ}}_{*},{\mathrm{\σ}}_{*}^2)d{f}_{*}=\mathrm{\Φ}\left(\frac{{\mathrm{\μ}}_{*}}{\sqrt{1+{\mathrm{\σ}}_{*}^2}}\right)---\left(6\right)$

θ is the ultra parameter of model; Influence to probability estimate is bigger, therefore when model construction, needs to confirm in advance ultra parameter θ; The present invention adopts the maximum likelihood function estimation technique to ask for ultra parameter θ; The maximum likelihood estimation technique is the maximal value through the likelihood function of finding the solution ultra parameter, and then the ultra parameter of seeking optimumly, like formula (7)

p(D|θ)＝∫p(y|f)p(f|X，θ)df (7)

Detection sample x for two classification _*, can set and work as x _*Belong to positive type probability q (y _*=1|D, θ, x _*)＞0.5 o'clock then is divided into positive type with it, promptly should be constantly for adjustment constantly; Otherwise, it is divided into negative type, promptly should constantly be the non-adjustment moment.The nicety of grading of distinct methods is more as shown in table 1:

Table 1Laplace method, expectation Law of Communication and SVMs method nicety of grading are relatively

Step 3: set up fuzzy rule base

Foundation is based on the fuzzy rule base of If-Then fuzzy rule, and idiographic flow is following:

1. the corresponding constantly generating unit data and the input sample of consumable unit data of adjustment that step 2 classification obtained as fuzzy rule base, corresponding output sample for adjustment constantly correspondence by the adjustment unit classification;

2. will import sample space and output sample spatial division is fuzzy field, promptly through to input sample, output sample analysis, draws the best cluster number of coal gas system generating unit data and consumable unit data, makes it can complete reflection import the characteristic of sample;

3. use the fuzzy C-means clustering algorithm to the input sample section of carrying out cluster, and write down the classification under every segment data, produce initial fuzzy rule base based on the If-Then fuzzy rule;

3. 4. write down the degree of membership of affiliated each classification of every segment data;

5. simplify fuzzy rule base, reject identical input sample, the fuzzy rule of identical output sample, with identical input sample, the fuzzy rule of different output samples is merged into a fuzzy rule, explains that current time has a plurality of adjustment units that the coal gas system balance is adjusted.

Step 4: real-time online is confirmed adjustment unit

The monitoring coal gas system moves the unbalanced moment; Generating unit data and consumable unit data that this is corresponding constantly; Use the fuzzy C-means clustering algorithm to turn to the If-Then fuzzy rule; Compare with the fuzzy rule base that step 3 is set up, find out with fuzzy rule base in the most close fuzzy rule, but its output sample is exactly the adjustment unit of current time.

From spot database, take out some data points that need adjust and carry out confirmatory experiment, the errors of experimental data statistical form is as shown in table 2:

Table 2 error statistics table

Among the present invention coal gas system by the adjustment unit classification by letter representation, specifically be expressed as: boiler of A-power plant, No. two boilers of B-power plant, No. four generators of C-, D-low-pressure boiler.

Step 5: the calculating of adjustment total amount

Adopt the adjustment total amount of Difference Calculation method acquisition coal gas system, following in conjunction with accompanying drawing 3 idiographic flows:

In the time period of transfiniting in the gas chamber position, select three cabinet positions t that transfinites ₁, t ₂, t ₃Suppose when initial

The gas chamber place value of carving is gh _i, so at t ₁The gas chamber place value can be described as constantly:

${\mathrm{<figure-callout\; id="1"\; label="gh"\; filenames="HDA00001853496100031.png"\; state="\{\{state\}\}">gh</figure-callout>}}_1={\mathrm{gh}}_i+\underset{t=1}{\overset{{\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HDA00001853496100031.png"\; state="\{\{state\}\}">t</figure-callout>}}_1}{\mathrm{\&Sigma;}}}{\mathrm{dflow}}_1\left(t\right)---\left(8\right)$

Dflow wherein ₁(t) be the generating unit data of t moment coal gas system and the flow difference of consumable unit data, in like manner also can be in the hope of gh ₂And gh ₃If the desired value gh when normal level is adjusted in the gas chamber position _o, defining adjusted coal gas system is dflow in the flow difference of t moment generating unit data and consumable unit data _o(t), gh so _oCan be expressed as:

${\mathrm{gh}}_o={\mathrm{gh}}_i+\underset{t=0}{\overset{{\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HDA00001853496100031.png"\; state="\{\{state\}\}">t</figure-callout>}}_1}{\mathrm{\&Sigma;}}}{\mathrm{dflow}}_o\left(t\right)---\left(9\right)$

With formula (8) and (9) subtract each other formula (10), further, formula (10) can be write a Chinese character in simplified form an accepted way of doing sth (11);

${\mathrm{gh}}_1-{\mathrm{gh}}_o=\underset{t=0}{\overset{t_1}{\mathrm{\&Sigma;}}}[{\mathrm{dflow}}_1\left(t\right)-{\mathrm{dflow}}_o\left(t\right)]---\left(10\right)$

Δgh ₁＝t ₁·Δdflow ₁ (11)

In the time of so just can a little being transferred to desired value in the hope of being transfinited in three cabinet positions, the variable quantity of flow difference: Δ dflow ₁=Δ gh ₁/ t ₁, Δ dflow ₂=Δ gh ₂/ t ₂, Δ dflow ₃=Δ gh ₃/ t ₃

Further obtain the adjustment total amount based on formula (12).

Δdflow＝max{Δdflow ₁，Δdflow ₂，Δdflow ₃} (12)

Step 6: the adjustment amount that distributes each adjustment unit

According to the adjustment unit that obtains in the step 4,, the adjustment total amount that step 5 obtains is distributed to different adjustment units according to the priority of on-the-spot adjustment unit and the peak load ability of each adjustment unit.

Claims (1)

1. real-time balance adjustment method of metallurgical coal gas system based on statistical classification, its characteristic comprises the steps:

(1) from metallurgical coal gas system for field real-time data base read required adjustment unit data, by adjustment unit classification, generating unit data, consumable unit data, gas-holder location data;

(2) set up Gaussian process two disaggregated models

${\mathrm{\&mu;}}_{*}=k_{*}^T{K}^{-1}m,$ ${\mathrm{\&sigma;}}_{*}^2=K(x_{*},x_{*})-k_{*}^T(K^{-1}-K^{-1}{\mathrm{AK}}^{-1})k_{*}---\left(5\right)$

According to formula (4) and expectation computing formula, given detection sample x _*, output sample y then _*The approximate table that belongs to the probability of classification 1 is shown:

$q(y_{*}=1|D,\mathrm{\&theta;},x_{*})=\&Integral;\mathrm{\&Phi;}\left(f_{*}\right)N\left(f_{*}\right|{\mathrm{\&mu;}}_{*},{\mathrm{\&sigma;}}_{*}^2){\mathrm{df}}_{*}=\mathrm{\&Phi;}\left(\frac{{\mathrm{\&mu;}}_{*}}{\sqrt{1+{\mathrm{\&sigma;}}_{*}^2}}\right)---\left(6\right)$

Adopt the maximum likelihood function estimation technique to ask for ultra parameter θ, i.e. the maximal value of the likelihood function through finding the solution ultra parameter, and then the ultra parameter of seeking is optimumly seen formula (7)

p(D|θ)＝∫p(y|f)p(f|X，θ)df (7)

Detection sample x for two classification _*, set and work as x _*Belong to positive type probability q (y _*=1|D, θ, x _*)＞0.5 o'clock then is divided into positive type with it, promptly should be constantly for adjustment constantly; Otherwise, it is divided into negative type, promptly should constantly be the non-adjustment moment;

(3) set up fuzzy rule base

1. the corresponding constantly generating unit data and the input sample of consumable unit data of adjustment that step (2) classification obtained as fuzzy rule base, corresponding output sample for adjustment constantly correspondence by the adjustment unit classification;

2. will import sample space and output sample spatial division is fuzzy field, promptly through to input sample, output sample analysis, draws the best cluster number of coal gas system generating unit data and consumable unit data, makes it can complete reflection import the characteristic of sample;

3. use the fuzzy C-means clustering algorithm to the input sample section of carrying out cluster, and write down the classification under every segment data, produce initial fuzzy rule base based on the If-Then fuzzy rule;

4. write down the degree of membership of affiliated each classification of every segment data;

5. simplify fuzzy rule base, reject identical input sample, the fuzzy rule of identical output sample, with identical input sample, the fuzzy rule of different output samples is merged into a fuzzy rule, explains that current time has a plurality of adjustment units that the coal gas system balance is adjusted;

(4) real-time online is confirmed adjustment unit

The monitoring coal gas system moves the unbalanced moment; Generating unit data and consumable unit data that this is corresponding constantly; Use the fuzzy C-means clustering algorithm to turn to the If-Then fuzzy rule; Compare with the fuzzy rule base that step (3) is set up; Find out with fuzzy rule base in the most close fuzzy rule, but its output sample is exactly the adjustment unit of current time;

(5) calculating of adjustment total amount adopts the acquisition of Difference Calculation method to need the coal gas total amount of adjustment, and idiographic flow is following:

In the time period of transfiniting in the gas chamber position, select three cabinet positions t that transfinites ₁, t ₂, t ₃Suppose that the gas chamber place value at initial time t=0 is gh _i, so at t ₁The gas chamber place value is described as constantly:

${\mathrm{gh}}_1={\mathrm{gh}}_i+\underset{t=1}{\overset{t_1}{\mathrm{\&Sigma;}}}{\mathrm{dflow}}_1\left(t\right)---\left(8\right)$

In like manner, try to achieve gh ₂And gh ₃

If the desired value gh when normal level is adjusted in the gas chamber position _o, defining adjusted coal gas system is dflow in the flow difference of t moment generating unit data and consumable unit data _o(t), gh so _oBe expressed as:

${\mathrm{gh}}_o={\mathrm{gh}}_i+\underset{t=1}{\overset{t_1}{\mathrm{\&Sigma;}}}{\mathrm{dflow}}_o\left(t\right)---\left(9\right)$

With formula (8) and (9) subtract each other formula (10), further, formula (10) is write a Chinese character in simplified form an accepted way of doing sth (11);

${\mathrm{gh}}_1-{\mathrm{gh}}_o=\underset{t=0}{\overset{t_1}{\mathrm{\&Sigma;}}}[{\mathrm{dflow}}_1\left(t\right)-{\mathrm{dflow}}_o\left(t\right)]---\left(10\right)$

Δgh ₁＝t ₁·Δdflow ₁ (11)

Trying to achieve with this transfinites three cabinet positions when a little being transferred to desired value the variable quantity of flow difference:

Δdflow ₁＝Δgh ₁/t ₁，

Δdflow ₂＝Δgh ₂/t ₂，

Δdflow ₃＝Δgh ₃/t ₃；

Further obtain the adjustment total amount according to formula (12):

Δdflow＝maX{Δdflow ₁，Δdflow ₂，Δdflow ₃} (12)

(6) distribute the adjustment amount of each adjustment unit

According to the adjustment unit that obtains in the step (4),, the adjustment total amount that step (5) obtains is distributed to different adjustment units according to the priority of on-the-spot adjustment unit and the peak load ability of each adjustment unit.

Images