CN103423741A - Energy-saving optimal system and method for circulating fluidized bed boiler - Google Patents

Abstract

The invention discloses an energy-saving optimal system and method for a circulating fluidized bed boiler. The system comprises a field intelligent instrument, a database, a data interface, a control station and an upper computer which are connected with the circulating fluidized bed boiler, wherein the field intelligent instrument is connected with the control station, the database and the upper computer; the upper computer comprises an energy loss prediction module used for predicting the total energy loss rate generated by the boiler if the circulating fluidized bed boiler runs according to the value of a preset operating variable under current running conditions, a restriction judgment module used for judging whether the preset operating variable meets the process requirements of the circulating fluidized bed boiler under conventional working conditions, an optimization search module used for searching an optimal operating variable, a signal acquisition module and a result display module. According to the system, the energy loss is fully reduced and the production benefit is increased through the optimization of the operating variable on the promise of guaranteeing that steam parameters and steam output meet the production requirements.

Description

The energy-conservation optimization system of CFBB and method

Technical field

The present invention relates to the energy project field, especially, relate to the energy-conservation optimization system of a kind of CFBB and method.

Background technology

CFBB has the advantages such as pollutant emission is few, fuel tolerance wide, the Load Regulation ability is strong, in the industries such as electric power, heat supply, obtains applying more and more widely in recent years.Along with the growing tension of the energy and the continuous enhancing of people's energy-conserving and environment-protective consciousness, the user is excavated in the urgent need to the operation potentiality to the boiler unit, improves the operational efficiency of unit.Yet current most of CFBB all exists automaticity low, operation relies on the characteristics of artificial experience, makes the energy-saving potential of boiler be difficult to be taped the latent power fully.Set up effective energy-conservation optimization system, fully improve the energy efficiency of CFBB, there is important practical significance.

Summary of the invention

The object of the invention is to for the deficiencies in the prior art, a kind of CFBB heat loss due to exhaust gas prognoses system and method are provided.

The technical solution adopted for the present invention to solve the technical problems is: the energy-conservation optimization system of a kind of CFBB comprises the field intelligent instrument, database, data-interface, control station and the host computer that are connected with CFBB; Field intelligent instrument is connected with control station, database and host computer, and described host computer comprises:

The energy loss prediction module, for the prediction loop fluidized-bed combustion boiler, under current service condition, if by default performance variable value operation, boiler, by the total energy loss rate produced, adopts following process to complete:

1.1) gather the historical record of operation variable and service condition variable from database, form the training sample matrix X of independent variable, gather corresponding energy loss correlated variables, form dependent variable training sample matrix Y, note:

$X=\left(\begin{array}{ccccc}1& x_{\mathrm{1,1}}& x_{\mathrm{1,2}}& ...& x_{\mathrm{1,11}}\\ 1& x_{\mathrm{2,1}}& x_{\mathrm{2,2}}& ...& x_{\mathrm{2,11}}\\ ...& ...& ...& ...& ...\\ 1& x_{n,1}& x_{n,2}& ...& x_{n,11}\end{array}\right),Y=\left(\begin{array}{cccc}{y}_{\mathrm{1,1}}& y_{\mathrm{1,2}}& ...& y_{\mathrm{1,7}}\\ y_{\mathrm{2,1}}& y_{\mathrm{2,2}}& ...& y_{\mathrm{2,7}}\\ ...& ...& ...& ...\\ y_{n,1}& y_{n,2}& ...& y_{n,7}\end{array}\right)---\left(1\right)$

X wherein _{I, 1}, x _{I, 2}..., x _{I, 11}Mean respectively a wind total blast volume (Nm3/h), Secondary Air total blast volume (Nm3/h), main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press i training sample value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y _{I, 1}, y _{I, 2}..., y _{I, 7}Mean respectively excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), i training sample value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A); N is the training sample number.

1.2) ask prediction coefficient matrix β by following formula:

β=(X ^TX) ^-1X ^TY （2）

Wherein, subscript: T ,-1 is transposition, the inverse of a matrix of representing matrix respectively.

1.3) gather the live signal of service condition variable from field intelligent instrument, the current preset value of binding operation variable, ask the predicted value of energy loss correlated variables by following formula:

[y ₁ y ₂ ... y ₇]=[1 x ₁ x ₂ ... x ₁₁]β （3）

Wherein, x ₁, x ₂Mean respectively performance variable: a wind total blast volume (Nm ³/ h), Secondary Air total blast volume (Nm ³/ h) current preset value; x ₃, x ₄..., x ₁₁Mean respectively the service condition variable: main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press the instantaneous value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y ₁, y ₂..., y ₇Mean respectively the energy loss correlated variables: excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), the predicted value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A).

1.4) ask for the predicted value of the rate of energy loss of respectively itemizing by (4)～(6) formula:

$q_2=(K_1{y}_1+K_2)\frac{y_3}{10000}---\left(4\right)$

${\mathrm{<figure-callout\; id="4"\; label="q"\; filenames="130804134107.png"\; state="\{\{state\}\}">q</figure-callout>}}_4=312.23\frac{x_{10}}{x_{12}}\&times;\frac{y_4}{100-y_4}---\left(5\right)$

p _f=f _p(y ₅,y ₆,y ₇,x ₃) （6）

Wherein, K ₁, K ₂For the design factor relevant with coal, for common bituminous coal, get K ₁=3.35, K ₂=0.44; q ₂For heat loss due to exhaust gas rate predicted value, heat loss due to exhaust gas accounts for the predicted value that boiler is always inputted the ratio of heat; x ₁₂For coal-fired As-received low heat valve (kJ/kg); q ₄For solid-unburning hot loss rate predicted value, solid-unburning hot loss accounts for the predicted value that boiler is always inputted the ratio of heat; f _p() is each blower fan electric current of determining according to physical device and the functional relation between boiler load and blower fan power consumption rate; p _fFor blower fan power consumption rate predicted value, the blower fan power consumption accounts for the predicted value that boiler is always inputted the ratio of heat.

1.5) ask for the predicted value of total energy loss rate by following formula:

q _all=f(X)=q ₂+q ₄+k _ep _f （7）

Wherein, q _allFor total energy loss rate predicted value, the total energy loss of boiler accounts for the predicted value that boiler is always inputted the ratio of heat; k _eValue ratio for electric energy and heat energy; F (X) means that the total energy loss rate is the function of performance variable collection X.

The constraint judge module, for judging whether default performance variable, under current working, meets the technological requirement of CFBB, adopts following process to complete:

2.1) energy loss correlated variables that service condition variable, default performance variable and prediction are obtained, substitution (8)～(12) formula:

f _pmin≤x ₁≤f _pmax （8）

f _smin≤x ₂≤f _smax （9）

t _bmin≤y ₂≤t _bmax （10）

x ₄+y ₃≥t _pmin （11）

x ₁+x ₂≥k _fminx ₃ （12）

Wherein, f _PminFor minimum primary air flow, f _PmaxFor maximum primary air flow, f _SminFor minimum secondary air flow, f _SmaxFor the maximum secondary air quantity, _TbminFor minimum operation bed temperature, t _BmaxFor the highest operation bed temperature, t _PminFor minimum exhaust gas temperature, k _FminFor minimum wind load ratio.

2.2) if (8)～(12) formula is all set up, judge that default performance variable is as feasible, otherwise judge that default performance variable is as infeasible.

The optimizing module, for finding optimum performance variable, adopts following process to complete:

3.1) produce a random point X (x by (13), (14) formula take in the two dimensional surface that primary air flow, secondary air flow be reference axis ₁, x ₂):

x ₁=f _pmin+r ₁(f _pmax-f _pmin) （13）

x ₂=f _smin+r ₂(f _smax-f _smin) （14）

Wherein, r ₁, r ₂For (0,1) interval 2 interior pseudo random numbers.

3.2) whether feasible by constraint judge module judging point X, if some X is feasible, make initial point X ⁽⁰⁾=X, otherwise go to step 3.1) produce new random point, until the random point X produced is feasible.

3.3) produce k by following formula _dIndividual random units vector:

e _j=[sin(2πq _j),cos(2πq _j)]，（j=1,2,...k _d) （15）

Wherein, k _dFor random units vector number, q _jFor (0,1) interval j interior pseudo random number, e _jBe j random units vector.

3.4) setting initial trial step-length α ₀.

3.5) produce k by following formula _dIndividual random point:

X ^(j)=X ⁽⁰⁾+α ₀e _j，（j=1,2,...k _d） （16）

Wherein, α ₀For test step-length, X ^(j)Be j random point unit vector number.

3.6) by constraint judge module judgement k _dIndividual random point X ^(j)Whether feasible, feasible random point is predicted to its total energy loss f (X by the energy loss prediction module ^(j)), the total energy loss of each feasible random point relatively, select the feasible random point of total energy loss minimum, is designated as X ^(L).

3.7) comparison f (X ^(L)) and f (X ⁽⁰⁾), if f is (X ^(L))<f (X ⁽⁰⁾), make S=X ^(L)-X ⁽⁰⁾Go to step 3.9), otherwise get

Return to step 3.5) regenerate k _dIndividual random point.

3.8) if α ₀<1 * 10 ^-10, still can not find an X ^(L)Make f (X ^(L))<f (X ⁽⁰⁾), go to step 3.11).

3.9) make S=1.2S.

3.10) comparison f (X ^(L)) and f (X ^(L)+ S), if f is (X ^(L)+ S)<f (X ^(L)), make X ^(L)=X ^(L)+ S, return to step 3.9), otherwise make X ⁽⁰⁾=X ^(L), return to step 3.3) and carry out next step optimizing.

3.11) X ⁽⁰⁾Be optimum point, the component that it is corresponding

Be optimum primary air flow and optimum secondary air flow.

As preferred a kind of scheme: described host computer also comprises:

Signal acquisition module, for the sampling time interval by setting, gather real time data from field intelligent instrument, and gather historical data from database.

Display module as a result, for from control station, reading parameters, and pass to control station by optimum primary air flow, Secondary Air value and shown, so that the control station staff, according to suggestion for operation, timely adjusting operation condition, reduce the boiler energy loss, improve boiler operating efficiency.

The energy-conservation optimal method of a kind of CFBB, described energy-conservation optimal method comprises the following steps:

1) the prediction loop fluidized-bed combustion boiler is under current service condition, if by default performance variable value operation, boiler, by the total energy loss rate produced, adopts following process to complete:

1.1) gather the historical record of operation variable and service condition variable from database, form the training sample matrix X of independent variable, gather corresponding energy loss correlated variables, form dependent variable training sample matrix Y, note:

$X=\left(\begin{array}{ccccc}1& x_{\mathrm{1,1}}& x_{\mathrm{1,2}}& ...& x_{\mathrm{1,11}}\\ 1& x_{\mathrm{2,1}}& x_{\mathrm{2,2}}& ...& x_{\mathrm{2,11}}\\ ...& ...& ...& ...& ...\\ 1& x_{n,1}& x_{n,2}& ...& x_{n,11}\end{array}\right),Y=\left(\begin{array}{cccc}{y}_{\mathrm{1,1}}& y_{\mathrm{1,2}}& ...& y_{\mathrm{1,7}}\\ y_{\mathrm{2,1}}& y_{\mathrm{2,2}}& ...& y_{\mathrm{2,7}}\\ ...& ...& ...& ...\\ y_{n,1}& y_{n,2}& ...& y_{n,7}\end{array}\right)---\left(1\right)$

X wherein _{I, 1}, x _{I, 2}..., x _{I, 11}Mean respectively wind total blast volume (Nm one time ³/ h), Secondary Air total blast volume (Nm ³/ h), main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press i training sample value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y _{I, 1}, y _{I, 2}..., y _{I, 7}Mean respectively excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), i training sample value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A); N is the training sample number.

1.2) ask prediction coefficient matrix β by following formula:

β=(X ^TX) ^-1X ^TY （2）

Wherein, subscript: T ,-1 is transposition, the inverse of a matrix of representing matrix respectively.

1.3) gather the live signal of service condition variable from field intelligent instrument, the current preset value of binding operation variable, ask the predicted value of energy loss correlated variables by following formula:

[y ₁ y ₂ ... y ₇]=[1 x ₁ x ₂ ... x ₁₁]β （3）

Wherein, x ₁, x ₂Mean respectively performance variable: a wind total blast volume (Nm ³/ h), Secondary Air total blast volume (Nm ³/ h) current preset value; x ₃, x ₄..., x ₁₁Mean respectively the service condition variable: main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press the instantaneous value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y ₁, y ₂..., y ₇Mean respectively the energy loss correlated variables: excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), the predicted value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A).

1.4) ask for the predicted value of the rate of energy loss of respectively itemizing by (4)～(6) formula:

${\mathrm{<figure-callout\; id="2"\; label="q"\; filenames="130804134107.png"\; state="\{\{state\}\}">q</figure-callout>}}_2=(K_1{y}_1+K_2)\frac{y_3}{10000}---\left(4\right)$

${\mathrm{<figure-callout\; id="4"\; label="q"\; filenames="130804134107.png"\; state="\{\{state\}\}">q</figure-callout>}}_4=312.23\frac{x_{10}}{x_{12}}\&times;\frac{{\mathrm{<figure-callout\; id="4"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>}}_4}{100-y_4}---\left(5\right)$

p _f=f _p(y ₅,y ₆,y ₇,x ₃) （6）

Wherein, K ₁, K ₂For the design factor relevant with coal, for common bituminous coal, get K ₁=3.35, K ₂=0.44; q ₂For heat loss due to exhaust gas rate predicted value, heat loss due to exhaust gas accounts for the predicted value that boiler is always inputted the ratio of heat; x ₁₂For coal-fired As-received low heat valve (kJ/kg); q ₄For solid-unburning hot loss rate predicted value, solid-unburning hot loss accounts for the predicted value that boiler is always inputted the ratio of heat; f _p() is each blower fan electric current of determining according to physical device and the functional relation between boiler load and blower fan power consumption rate; p _fFor blower fan power consumption rate predicted value, the blower fan power consumption accounts for the predicted value that boiler is always inputted the ratio of heat.

1.5) ask for the predicted value of total energy loss rate by following formula:

q _all=f(X)=q ₂+q ₄+k _ep _f （7）

Wherein, q _allFor total energy loss rate predicted value, the total energy loss of boiler accounts for the predicted value that boiler is always inputted the ratio of heat; k _eValue ratio for electric energy and heat energy; F (X) means that the total energy loss rate is the function of performance variable collection X.

2) judge whether default performance variable, under current working, meets the technological requirement of CFBB, adopt following process to complete:

2.1) energy loss correlated variables that service condition variable, default performance variable and prediction are obtained, substitution (8)～(12) formula:

f _pmin≤x ₁≤f _pmax （8）

f _smin≤x ₂≤f _smax （9）

t _bmin≤y ₂≤t _bmax （10）

x ₄+y ₃≥t _pmin （11）

x ₁+x ₂≥k _fminx ₃ （12）

Wherein, f _PminFor minimum primary air flow, f _PmaxFor maximum primary air flow, f _SminFor minimum secondary air flow, f _SmaxFor maximum secondary air quantity, t _BminFor minimum operation bed temperature, t _BmaxFor the highest operation bed temperature, t _PminFor minimum exhaust gas temperature, k _FminFor minimum wind load ratio.

2.2) if (8)～(12) formula is all set up, judge that default performance variable is as feasible, otherwise judge that default performance variable is as infeasible.

3) find optimum performance variable, adopt following process to complete:

3.1) produce a random point X (x by (13), (14) formula take in the two dimensional surface that primary air flow, secondary air flow be reference axis ₁, x ₂):

x ₁=f _pmin+r ₁(f _pmax-f _pmin) （13）

x ₂=f _smin+r ₂(f _smax-f _smin) （14）

Wherein, r ₁, r ₂For (0,1) interval 2 interior pseudo random numbers.

3.2) by step 2) whether judging point X feasible, if some X is feasible, makes initial point X ⁽⁰⁾=X, otherwise go to step 3.1) produce new random point, until the random point X produced is feasible.

3.3) produce k by following formula _dIndividual random units vector:

e _j=[sin(2πq _j),cos(2πq _j)]，（j=1,2,...k _d) （15）

Wherein, k _dFor random units vector number, q _jFor (0,1) interval j interior pseudo random number, e _jBe j random units vector.

3.4) setting initial trial step-length α ₀.

3.5) produce k by following formula _dIndividual random point:

X ^(j)=X ⁽⁰⁾+α ₀e _j，（j=1,2,...k _d） （16）

Wherein, α ₀For test step-length, X ^(j)Be j random point unit vector number.

3.6) by step 2) judgement k _dIndividual random point X ^(j)Whether feasible, feasible random point is predicted to its total energy loss f (X by step 1) ^(j)), the total energy loss of each feasible random point relatively, select the feasible random point of total energy loss minimum, is designated as X ^(L).

3.7) comparison f (X ^(L)) and f (X ⁽⁰⁾), if f is (X ^(L))<f (X ⁽⁰⁾), make S=X ^(L)-X ⁽⁰⁾Go to step 3.9), otherwise get

Return to step 3.5) regenerate k _dIndividual random point.

3.8) if α ₀<1 * 10 ^-10, still can not find an X ^(L)Make f (X ^(L))<f (X ⁽⁰⁾), go to step 3.11).

3.9) make S=1.2S.

3.10) comparison f (X ^(L)) and f (X ^(L)+ S), if f is (X ^(L)+ S)<f (X ^(L)), make X ^(L)=X ^(L)+ S, return to step 3.9), otherwise make X ⁽⁰⁾=X ^(L), return to step 3.3) and carry out next step optimizing.

3.11) X ⁽⁰⁾Be optimum point, the component that it is corresponding Be optimum primary air flow and optimum secondary air flow.

As preferred a kind of scheme: in described step 3), read parameters from control station, and optimum primary air flow, Secondary Air value are passed to control station shown, so that control station staff, according to suggestion for operation, the adjusting operation condition, reduce the boiler energy loss in time, improves boiler operating efficiency.

Beneficial effect of the present invention is mainly manifested in: the performance variable to CFBB is optimized, and suggestion and guides production operation, reduces the boiler energy loss, excavates the device energy-saving potential, improves productivity effect.

The accompanying drawing explanation

Fig. 1 is the hardware structure diagram of system proposed by the invention.

Fig. 2 is the functional block diagram of host computer of the present invention.

The specific embodiment

Below in conjunction with drawings and Examples, the invention will be further described.

Embodiment 1

With reference to Fig. 1, Fig. 2, the energy-conservation optimization system of a kind of CFBB, comprise the field intelligent instrument 2, data-interface 3, database 4, control station 5 and the host computer 6 that are connected with CFBB 1, field intelligent instrument 2 is connected with fieldbus, data/address bus is connected with data-interface 3, data-interface 3 is connected with database 4, control station 5 and host computer 6, and described host computer 6 comprises:

Energy loss prediction module 7, for the prediction loop fluidized-bed combustion boiler, under current service condition, if by default performance variable value operation, boiler, by the total energy loss rate produced, adopts following process to complete:

1.1) gather the historical record of operation variable and service condition variable from database, form the training sample matrix X of independent variable, gather corresponding energy loss correlated variables, form dependent variable training sample matrix Y, note:

$X=\left(\begin{array}{ccccc}1& x_{\mathrm{1,1}}& x_{\mathrm{1,2}}& ...& x_{\mathrm{1,11}}\\ 1& x_{\mathrm{2,1}}& x_{\mathrm{2,2}}& ...& x_{\mathrm{2,11}}\\ ...& ...& ...& ...& ...\\ 1& x_{n,1}& x_{n,2}& ...& x_{n,11}\end{array}\right),Y=\left(\begin{array}{cccc}{y}_{\mathrm{1,1}}& {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>}}_{\mathrm{1,2}}& ...& y_{\mathrm{1,7}}\\ {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>}}_{\mathrm{2,1}}& {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">\; <figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>\; </figure-callout>}}_{\mathrm{2,2}}& ...& {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">\; <figure-callout\; id="7"\; label="y"\; filenames="130804134111.png"\; state="\{\{state\}\}">y</figure-callout>\; </figure-callout>}}_{\mathrm{2,7}}\\ ...& ...& ...& ...\\ y_{n,1}& y_{n,2}& ...& y_{n,7}\end{array}\right)---\left(1\right)$

X wherein _{I, 1}, x _{I, 2}..., x _{I, 11}Mean respectively wind total blast volume (Nm one time ³/ h), Secondary Air total blast volume (Nm ³/ h), main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press i training sample value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y _{I, 1}, y _{I, 2}..., y _{I, 7}Mean respectively excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), i training sample value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A); N is the training sample number.

1.2) ask prediction coefficient matrix β by following formula:

β=(X ^TX) ^-1X ^TY （2）

Wherein, subscript: T ,-1 is transposition, the inverse of a matrix of representing matrix respectively.

1.3) gather the live signal of service condition variable from field intelligent instrument, the current preset value of binding operation variable, ask the predicted value of energy loss correlated variables by following formula:

[y ₁ y ₂ ... y ₇]=[1 x ₁ x ₂ ... x ₁₁]β （3）

Wherein, x ₁, x ₂Mean respectively performance variable: a wind total blast volume (Nm ³/ h), Secondary Air total blast volume (Nm ³/ h) current preset value; x ₃, x ₄..., x ₁₁Mean respectively the service condition variable: main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press the instantaneous value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y ₁, y ₂..., y ₇Mean respectively the energy loss correlated variables: excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), the predicted value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A).

1.4) ask for the predicted value of the rate of energy loss of respectively itemizing by (4)～(6) formula:

${\mathrm{<figure-callout\; id="2"\; label="q"\; filenames="130804134107.png"\; state="\{\{state\}\}">q</figure-callout>}}_2=(K_1{y}_1+K_2)\frac{y_3}{10000}---\left(4\right)$

${\mathrm{<figure-callout\; id="4"\; label="q"\; filenames="130804134107.png"\; state="\{\{state\}\}">q</figure-callout>}}_4=312.23\frac{x_{10}}{x_{12}}\&times;\frac{{\mathrm{<figure-callout\; id="4"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>}}_4}{100-y_4}---\left(5\right)$

p _f=f _p(y ₅,y ₆,y ₇,x ₃) （6）

Wherein, K ₁, K ₂For the design factor relevant with coal, for common bituminous coal, get K ₁=3.35, K ₂=0.44; q ₂For heat loss due to exhaust gas rate predicted value, heat loss due to exhaust gas accounts for the predicted value that boiler is always inputted the ratio of heat; x ₁₂For coal-fired As-received low heat valve (kJ/kg); q ₄For solid-unburning hot loss rate predicted value, solid-unburning hot loss accounts for the predicted value that boiler is always inputted the ratio of heat; f _p() is each blower fan electric current of determining according to physical device and the functional relation between boiler load and blower fan power consumption rate; p _fFor blower fan power consumption rate predicted value, the blower fan power consumption accounts for the predicted value that boiler is always inputted the ratio of heat.

1.5) ask for the predicted value of total energy loss rate by following formula:

q _all=f(X)=q ₂+q ₄+k _ep _f （7）

Wherein, q _allFor total energy loss rate predicted value, the total energy loss of boiler accounts for the predicted value that boiler is always inputted the ratio of heat; k _eValue ratio for electric energy and heat energy; F (X) means that the total energy loss rate is the function of performance variable collection X.

Constraint judge module 9, for judging whether default performance variable, under current working, meets the technological requirement of CFBB, adopts following process to complete:

2.1) energy loss correlated variables that service condition variable, default performance variable and prediction are obtained, substitution (8)～(12) formula:

f _pmin≤x ₁≤f _pmax （8）

f _smin≤x ₂≤f _smax （9）

t _bmin≤y ₂≤t _bmax （10）

x ₄+y ₃≥t _pmin （11）

X ₁+ x ₂>=k _Fminx ₃(12) wherein, f _PminFor minimum primary air flow, f _PmaxFor maximum primary air flow, f _SminFor minimum secondary air flow, f _SmaxFor maximum secondary air quantity, t _BminFor minimum operation bed temperature, t _BmaxFor the highest operation bed temperature, t _PminFor minimum exhaust gas temperature, k _FminFor minimum wind load ratio.

2.2) if (8)～(12) formula is all set up, judge that default performance variable is as feasible, otherwise judge that default performance variable is as infeasible.

Optimizing module 8, for finding optimum performance variable, adopts following process to complete:

3.1) produce a random point X (x by (13), (14) formula take in the two dimensional surface that primary air flow, secondary air flow be reference axis ₁, x ₂):

x ₁=f _pmin+r ₁(f _pmax-f _pmin) （13）

x ₂=f _smin+r ₂(f _smax-f _smin) （14）

Wherein, r ₁, r ₂For (0,1) interval 2 interior pseudo random numbers.

3.2) whether feasible by constraint judge module 9 judging point X, if some X is feasible, make initial point X ⁽⁰⁾=X, otherwise go to step 3.1) produce new random point, until the random point X produced is feasible.

3.3) produce k by following formula _dIndividual random units vector:

e _j=[sin(2πq _j),cos(2πq _j)]，（j=1,2,...k _d） （15）

Wherein, k _dFor random units vector number, the present embodiment is got k _d=120, q _jFor (0,1) interval j interior pseudo random number, e _jBe j random units vector.

3.4) setting initial trial step-length α ₀, the present embodiment is got α ₀=0.0001.

3.5) produce k by following formula _dIndividual random point:

X ^(j)=X ⁽⁰⁾+α ₀e _j，（j=1,2,...k _d） （16）

Wherein, α ₀For test step-length, X ^(j)Be j random point unit vector number.

3.6) by constraint judge module 9 judgement k _dIndividual random point X ^(j)Whether feasible, feasible random point is predicted to its total energy loss f (X by energy loss prediction module 7 ^(j)), the total energy loss of each feasible random point relatively, select the feasible random point of total energy loss minimum, is designated as X ^(L).

3.7) comparison f (X ^(L)) and f (X ⁽⁰⁾), if f is (X ^(L))<f (X ⁽⁰⁾), make S=X ^(L)-X ⁽⁰⁾Go to step 3.9), otherwise get

Return to step 3.5) regenerate k _dIndividual random point.

3.8) if α ₀<1 * 10 ^-10, still can not find an X ^(L)Make f (X ^(L))<f (X ⁽⁰⁾), go to step 3.11).

3.9) make S=1.2S.

3.10) comparison f (X ^(L)) and f (X ^(L)+ S), if f is (X ^(L)+ S)<f (X ^(L)), make X ^(L)=X ^(L)+ S, return to step 3.9), otherwise make X ⁽⁰⁾=X ^(L), return to step 3.3) and carry out next step optimizing.

3.11) X ⁽⁰⁾Be optimum point, the component that it is corresponding

Be optimum primary air flow and optimum secondary air flow.

3.11) X ⁽⁰⁾Be optimum point, the component that it is corresponding

Be optimum primary air flow and optimum secondary air flow.

Described host computer 6 also comprises: signal acquisition module 11, for the sampling time interval by setting, gathers real time data from field intelligent instrument, and gather historical data from database.

Described host computer 6 also comprises: display module 10 as a result, for from control station, reading parameters, and optimum primary air flow, Secondary Air value are passed to control station shown, so that control station staff, according to suggestion for operation, the adjusting operation condition, reduce the boiler energy loss in time, improves boiler operating efficiency.

The hardware components of described host computer 6 comprises: the I/O element, for the collection of data and the transmission of information; Data storage, the data sample that storage running is required and operational factor etc.; Program storage, the software program of storage practical function module; Arithmetic unit, performing a programme, realize the function of appointment; Display module, show the parameter, the operation result that arrange, and provide suggestion for operation.

Embodiment 2

With reference to Fig. 1, Fig. 2, the energy-conservation optimal method of a kind of CFBB, described energy-conservation optimal method comprises the following steps:

1) the prediction loop fluidized-bed combustion boiler is under current service condition, if by default performance variable value operation, boiler, by the total energy loss rate produced, adopts following process to complete:

1.1) gather the historical record of operation variable and service condition variable from database, form the training sample matrix X of independent variable, gather corresponding energy loss correlated variables, form dependent variable training sample matrix Y, note:

$X=\left(\begin{array}{ccccc}1& x_{\mathrm{1,1}}& x_{\mathrm{1,2}}& ...& x_{\mathrm{1,11}}\\ 1& x_{\mathrm{2,1}}& x_{\mathrm{2,2}}& ...& x_{\mathrm{2,11}}\\ ...& ...& ...& ...& ...\\ 1& x_{n,1}& x_{n,2}& ...& x_{n,11}\end{array}\right),Y=\left(\begin{array}{cccc}{y}_{\mathrm{1,1}}& {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>}}_{\mathrm{1,2}}& ...& y_{\mathrm{1,7}}\\ {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>}}_{\mathrm{2,1}}& {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">\; <figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>\; </figure-callout>}}_{\mathrm{2,2}}& ...& {\mathrm{<figure-callout\; id="2"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">\; <figure-callout\; id="7"\; label="y"\; filenames="130804134111.png"\; state="\{\{state\}\}">y</figure-callout>\; </figure-callout>}}_{\mathrm{2,7}}\\ ...& ...& ...& ...\\ y_{n,1}& y_{n,2}& ...& y_{n,7}\end{array}\right)---\left(1\right)$

X wherein _{I, 1}, x _{I, 2}..., x _i, ₁₁Mean respectively wind total blast volume (Nm one time ³/ h), Secondary Air total blast volume (Nm ³/ h), main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press i training sample value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y _{I, 1}, y _{I, 2}..., y _{I, 7}Mean respectively excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), i training sample value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A); N is the training sample number.

1.2) ask prediction coefficient matrix β by following formula:

β=(X ^TX) ^-1X ^TY （2）

Wherein, subscript: T ,-1 is transposition, the inverse of a matrix of representing matrix respectively.

1.3) gather the live signal of service condition variable from field intelligent instrument, the current preset value of binding operation variable, ask the predicted value of energy loss correlated variables by following formula:

[y ₁ y ₂ ... y ₇]=[1 x ₁ x ₂ ... x ₁₁]β （3）

Wherein, x ₁, x ₂Mean respectively performance variable: a wind total blast volume (Nm ³/ h), Secondary Air total blast volume (Nm ³/ h) current preset value; x ₃, x ₄..., x ₁₁Mean respectively the service condition variable: main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press the instantaneous value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y ₁, y ₂..., y ₇Mean respectively the energy loss correlated variables: excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), the predicted value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A).

1.4) ask for the predicted value of the rate of energy loss of respectively itemizing by (4)～(6) formula:

${\mathrm{<figure-callout\; id="2"\; label="q"\; filenames="130804134107.png"\; state="\{\{state\}\}">q</figure-callout>}}_2=(K_1{y}_1+K_2)\frac{y_3}{10000}---\left(4\right)$

${\mathrm{<figure-callout\; id="4"\; label="q"\; filenames="130804134107.png"\; state="\{\{state\}\}">q</figure-callout>}}_4=312.23\frac{x_{10}}{x_{12}}\&times;\frac{{\mathrm{<figure-callout\; id="4"\; label="y"\; filenames="130804134107.png"\; state="\{\{state\}\}">y</figure-callout>}}_4}{100-y_4}---\left(5\right)$

p _f=f _p(y ₅,y ₆,y ₇,x ₃) （6）

Wherein, K ₁, K ₂For the design factor relevant with coal, for common bituminous coal, get K ₁=3.35, K ₂=0.44; q ₂For heat loss due to exhaust gas rate predicted value, heat loss due to exhaust gas accounts for the predicted value that boiler is always inputted the ratio of heat; x ₁₂For coal-fired As-received low heat valve (kJ/kg); q ₄For solid-unburning hot loss rate predicted value, solid-unburning hot loss accounts for the predicted value that boiler is always inputted the ratio of heat; f _p() is each blower fan electric current of determining according to physical device and the functional relation between boiler load and blower fan power consumption rate; p _fFor blower fan power consumption rate predicted value, the blower fan power consumption accounts for the predicted value that boiler is always inputted the ratio of heat.

1.5) ask for the predicted value of total energy loss rate by following formula:

q _all=f(X)=q ₂+q ₄+k _ep _f （7）

Wherein, q _allFor total energy loss rate predicted value, the total energy loss of boiler accounts for the predicted value that boiler is always inputted the ratio of heat; k _eValue ratio for electric energy and heat energy; F (X) means that the total energy loss rate is the function of performance variable collection X.

2) judge whether default performance variable, under current working, meets the technological requirement of CFBB, adopt following process to complete:

2.1) energy loss correlated variables that service condition variable, default performance variable and prediction are obtained, substitution (8)～(12) formula:

f _pmin≤x ₁≤f _pmax （8）

f _smin≤x ₂≤f _smax （9）

t _bmin≤y ₂≤t _bmax （10）

x ₄+y ₃≥t _pmin （11）

x ₁+x ₂≥k _fminx ₃ （12）

Wherein, f _PminFor minimum primary air flow, f _PmaxFor maximum primary air flow, f _SminFor minimum secondary air flow, f _SmaxFor maximum secondary air quantity, t _BminFor minimum operation bed temperature, t _BmaxFor the highest operation bed temperature, t _PminFor minimum exhaust gas temperature, k _FminFor minimum wind load ratio.

2.2) if (8)～(12) formula is all set up, judge that default performance variable is as feasible, otherwise judge that default performance variable is as infeasible.

3) find optimum performance variable, adopt following process to complete:

3.1) produce a random point X (x by (13), (14) formula take in the two dimensional surface that primary air flow, secondary air flow be reference axis ₁, x ₂):

x ₁=f _pmin+r ₁(f _pmax-f _pmin) （13）

x ₂=f _smin+r ₂(f _smax-f _smin) （14）

Wherein, r ₁, r ₂For (0,1) interval 2 interior pseudo random numbers.

3.2) by step 2) whether judging point X feasible, if some X is feasible, makes initial point X ⁽⁰⁾=X, otherwise go to step 3.1) produce new random point, until the random point X produced is feasible.

3.3) produce k by following formula _dIndividual random units vector:

e _j=[sin(2πq _j),cos(2πq _j)]，（j=1,2,...k _d） （15）

Wherein, k _dFor random units vector number, the present embodiment is got k _d=120, q _jFor (0,1) interval j interior pseudo random number, e _jBe j random units vector.

3.4) setting initial trial step-length α ₀, the present embodiment is got α ₀=0.0001.

3.5) produce k by following formula _dIndividual random point:

X ^(j)=X ⁽⁰⁾+α ₀e _j，（j=1,2,...k _d） （16）

Wherein, α ₀For test step-length, X ^(j)Be j random point unit vector number.

Claims (2)

1. the energy-conservation optimization system of CFBB, is characterized in that, comprises the field intelligent instrument, database, data-interface, control station and the host computer that are connected with CFBB; Field intelligent instrument is connected with control station, database and host computer, and described host computer comprises:

The energy loss prediction module, for the prediction loop fluidized-bed combustion boiler, under current service condition, if by default performance variable value operation, boiler, by the total energy loss rate produced, adopts following process to complete:

1.1) gather the historical record of operation variable and service condition variable from database, form the training sample matrix X of independent variable, gather corresponding energy loss correlated variables, form dependent variable training sample matrix Y, note:

$X=\left(\begin{array}{ccccc}1& x_{\mathrm{1,1}}& x_{\mathrm{1,2}}& ...& x_{\mathrm{1,11}}\\ 1& x_{\mathrm{2,1}}& x_{\mathrm{2,2}}& ...& x_{\mathrm{2,11}}\\ ...& ...& ...& ...& ...\\ 1& x_{n,1}& x_{n,2}& ...& x_{n,11}\end{array}\right),Y=\left(\begin{array}{cccc}{y}_{\mathrm{1,1}}& y_{\mathrm{1,2}}& ...& y_{\mathrm{1,7}}\\ y_{\mathrm{2,1}}& y_{\mathrm{2,2}}& ...& y_{\mathrm{2,7}}\\ ...& ...& ...& ...\\ y_{n,1}& y_{n,2}& ...& y_{n,7}\end{array}\right)---\left(1\right)$

X wherein _{I, 1}, x _{I, 2}..., x _{I, 11}Mean respectively a wind total blast volume (Nm3/h), Secondary Air total blast volume (Nm3/h), main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press i training sample value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y _{I, 1}, y _{I, 2}..., y _{I, 7}Mean respectively excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), i training sample value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A); N is the training sample number;

1.2) ask prediction coefficient matrix β by following formula:

β=(X ^TX) ^-1X ^TY （2）

Wherein, subscript: T ,-1 is transposition, the inverse of a matrix of representing matrix respectively;

1.3) gather the live signal of service condition variable from field intelligent instrument, the current preset value of binding operation variable, ask the predicted value of energy loss correlated variables by following formula:

[y ₁ y ₂ ... y ₇]=[1 x ₁ x ₂ ... x ₁₁]β （3）

Wherein, x ₁, x ₂Mean respectively performance variable: a wind total blast volume (Nm ³/ h), Secondary Air total blast volume (Nm ³/ h) current preset value; x ₃, x ₄..., x ₁₁Mean respectively the service condition variable: main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press the instantaneous value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y ₁, y ₂..., y ₇Mean respectively the energy loss correlated variables: excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), the predicted value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A);

1.4) ask for the predicted value of the rate of energy loss of respectively itemizing by (4)～(6) formula:

$q_2=(K_1{y}_1+K_2)\frac{y_3}{10000}---\left(4\right)$

$q_4=312.23\frac{x_{10}}{x_{12}}\&times;\frac{y_4}{100-y_4}---\left(5\right)$

p _f=f _p(y ₅,y ₆,y ₇,x ₃) （6）

Wherein, K ₁, K ₂For the design factor relevant with coal, for common bituminous coal, get K ₁=3.35, K ₂=0.44; q ₂For heat loss due to exhaust gas rate predicted value, heat loss due to exhaust gas accounts for the predicted value that boiler is always inputted the ratio of heat; x ₁₂For coal-fired As-received low heat valve (kJ/kg); q ₄For solid-unburning hot loss rate predicted value, solid-unburning hot loss accounts for the predicted value that boiler is always inputted the ratio of heat; f _p() is each blower fan electric current of determining according to physical device and the functional relation between boiler load and blower fan power consumption rate; p _fFor blower fan power consumption rate predicted value, the blower fan power consumption accounts for the predicted value that boiler is always inputted the ratio of heat;

1.5) ask for the predicted value of total energy loss rate by following formula:

q _all=f(X)=q ₂+q ₄+k _ep _f （7）

Wherein, q _allFor total energy loss rate predicted value, the total energy loss of boiler accounts for the predicted value that boiler is always inputted the ratio of heat; k _eValue ratio for electric energy and heat energy; F (X) means that the total energy loss rate is the function of performance variable collection X;

The constraint judge module, for judging whether default performance variable, under current working, meets the technological requirement of CFBB, adopts following process to complete:

2.1) energy loss correlated variables that service condition variable, default performance variable and prediction are obtained, substitution (8)～(12) formula:

f _pmin≤x ₁≤f _pmax （8）

f _smin≤x ₂≤f _smax （9）

t _bmin≤y ₂≤t _bmax （10）

x ₄+y ₃≥t _pmin （11）

x ₁+x ₂≥k _fminx ₃ （12）

Wherein, f _PminFor minimum primary air flow, f _PmaxFor maximum primary air flow, f _SminFor minimum secondary air flow, f _SmaxFor maximum secondary air quantity, t _BminFor minimum operation bed temperature, t _BmaxFor the highest operation bed temperature, t _PminFor minimum exhaust gas temperature, k _FminFor minimum wind load ratio;

2.2) if (8)～(12) formula is all set up, judge that default performance variable is as feasible, otherwise judge that default performance variable is as infeasible;

The optimizing module, for finding optimum performance variable, adopts following process to complete:

3.1) produce a random point X (x by (13), (14) formula take in the two dimensional surface that primary air flow, secondary air flow be reference axis ₁, x ₂):

x ₁=f _pmin+r ₁(f _pmax-f _pmin) （13）

x ₂=f _smin+r ₂(f _smax-f _smin) （14）

Wherein, r ₁, r ₂For (0,1) interval 2 interior pseudo random numbers;

3.2) whether feasible by constraint judge module judging point X, if some X is feasible, make initial point X ⁽⁰⁾=X, otherwise go to step 3.1) produce new random point, until the random point X produced is feasible;

3.3) produce k by following formula _dIndividual random units vector:

e _j=[sin(2πq _j),cos(2πq _j)]，（j=1,2,...k _d） （15）

Wherein, k _dFor random units vector number, q _jFor (0,1) interval j interior pseudo random number, e _jBe j random units vector;

3.4) setting initial trial step-length α ₀

3.5) produce k by following formula _dIndividual random point:

X ^(j)=X ⁽⁰⁾+α ₀e _j，（j=1,2,...k _d） （16）

Wherein, α ₀For test step-length, X ^(j)Be j random point unit vector number;

3.6) by constraint judge module judgement k _dIndividual random point X ^(j)Whether feasible, feasible random point is predicted to its total energy loss f (X by the energy loss prediction module ^(j)), the total energy loss of each feasible random point relatively, select the feasible random point of total energy loss minimum, is designated as X ^(L)

3.7) comparison f (X ^(L)) and f (X ⁽⁰⁾), if f is (X ^(L))<f (X ⁽⁰⁾), make S=X ^(L)-X ⁽⁰⁾Go to step 3.9), otherwise get

Return to step 3.5) regenerate k _dIndividual random point;

3.8) if α ₀<1 * 10 ^-10, still can not find an X ^(L)Make f (X ^(L))<f (X ⁽⁰⁾), go to step 3.11);

3.9) make S=1.2S;

3.10) comparison f (X ^(L)) and f (X ^(L)+ S), if f is (X ^(L)+ S)<f (X ^(L)), make X ^(L)=X ^(L)+ S, return to step 3.9), otherwise make X ⁽⁰⁾=X ^(L), return to step 3.3) and carry out next step optimizing;

3.11) X ⁽⁰⁾Be optimum point, the component that it is corresponding

Be optimum primary air flow and optimum secondary air flow;

Described host computer also comprises:

Signal acquisition module, for the sampling time interval by setting, gather real time data from field intelligent instrument, and gather historical data from database;

Display module as a result, for from control station, reading parameters, and pass to control station by optimum primary air flow, Secondary Air value and shown, so that the control station staff, according to suggestion for operation, timely adjusting operation condition, reduce the boiler energy loss, improve boiler operating efficiency.

2. the energy-conservation optimal method realized with the energy-conservation optimization system of CFBB claimed in claim 1, is characterized in that, described energy-conservation optimal method comprises the following steps:

1) the prediction loop fluidized-bed combustion boiler is under current service condition, if by default performance variable value operation, boiler, by the total energy loss rate produced, adopts following process to complete:

1.1) gather the historical record of operation variable and service condition variable from database, form the training sample matrix X of independent variable, gather corresponding energy loss correlated variables, form dependent variable training sample matrix Y, note:

$X=\left(\begin{array}{ccccc}1& x_{\mathrm{1,1}}& x_{\mathrm{1,2}}& ...& x_{\mathrm{1,11}}\\ 1& x_{\mathrm{2,1}}& x_{\mathrm{2,2}}& ...& x_{\mathrm{2,11}}\\ ...& ...& ...& ...& ...\\ 1& x_{n,1}& x_{n,2}& ...& x_{n,11}\end{array}\right),Y=\left(\begin{array}{cccc}{y}_{\mathrm{1,1}}& y_{\mathrm{1,2}}& ...& y_{\mathrm{1,7}}\\ y_{\mathrm{2,1}}& y_{\mathrm{2,2}}& ...& y_{\mathrm{2,7}}\\ ...& ...& ...& ...\\ y_{n,1}& y_{n,2}& ...& y_{n,7}\end{array}\right)---\left(1\right)$

X wherein _{I, 1}, x _{I, 2}..., x _{I, 11}Mean respectively wind total blast volume (Nm one time ³/ h), Secondary Air total blast volume (Nm ³/ h), main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press i training sample value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y _{I, 1}, y _{I, 2}..., y _{I, 7}Mean respectively excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), i training sample value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A); N is the training sample number;

1.2) ask prediction coefficient matrix β by following formula:

β=(X ^TX) ^-1X ^TY （2）

Wherein, subscript: T ,-1 is transposition, the inverse of a matrix of representing matrix respectively;

1.3) gather the live signal of service condition variable from field intelligent instrument, the current preset value of binding operation variable, ask the predicted value of energy loss correlated variables by following formula:

[y ₁ y ₂ ... y ₇]=[1 x ₁ x ₂ ... x ₁₁]β （3）

Wherein, x ₁, x ₂Mean respectively performance variable: a wind total blast volume (Nm ³/ h), Secondary Air total blast volume (Nm ³/ h) current preset value; x ₃, x ₄..., x ₁₁Mean respectively the service condition variable: main steam flow (t/h), environment temperature (℃), feed temperature (℃), combustion chamber draft (kPa), bed press the instantaneous value of (kPa), coal-fired moisture (%), coal-fired volatile matter (%), coal-fired ash content (%), coal-fired sulphur content (%); y ₁, y ₂..., y ₇Mean respectively the energy loss correlated variables: excess air coefficient, bed temperature (℃), the smoke evacuation temperature difference (℃), the predicted value of flying dust carbon containing percentage (%), primary air fan electric current (A), overfire air fan electric current (A), air-introduced machine electric current (A);

1.4) ask for the predicted value of the rate of energy loss of respectively itemizing by (4)～(6) formula:

$q_2=(K_1{y}_1+K_2)\frac{y_3}{10000}---\left(4\right)$

$q_4=312.23\frac{x_{10}}{x_{12}}\&times;\frac{y_4}{100-y_4}---\left(5\right)$

p _f=f _p(y ₅,y ₆,y ₇,x ₃) （6）

Wherein, K ₁, K ₂For the design factor relevant with coal, for common bituminous coal, get K ₁=3.35, K ₂=0.44; q ₂For heat loss due to exhaust gas rate predicted value, heat loss due to exhaust gas accounts for the predicted value that boiler is always inputted the ratio of heat; x ₁₂For coal-fired As-received low heat valve (kJ/kg); q ₄For solid-unburning hot loss rate predicted value, solid-unburning hot loss accounts for the predicted value that boiler is always inputted the ratio of heat; f _p() is each blower fan electric current of determining according to physical device and the functional relation between boiler load and blower fan power consumption rate; p _fFor blower fan power consumption rate predicted value, the blower fan power consumption accounts for the predicted value that boiler is always inputted the ratio of heat;

1.5) ask for the predicted value of total energy loss rate by following formula:

q _all=f(X)=q ₂+q ₄+k _ep _f （7）

Wherein, q _allFor total energy loss rate predicted value, the total energy loss of boiler accounts for the predicted value that boiler is always inputted the ratio of heat; k _eValue ratio for electric energy and heat energy; F (X) means that the total energy loss rate is the function of performance variable collection X;

2) judge whether default performance variable, under current working, meets the technological requirement of CFBB, adopt following process to complete:

2.1) energy loss correlated variables that service condition variable, default performance variable and prediction are obtained, substitution (8)～(12) formula:

f _pmin≤x ₁≤f _pmax （8）

f _smin≤x ₂≤f _smax （9）

t _bmin≤y ₂≤t _bmax （10）

x ₄+y ₃≥t _pmin （11）

x ₁+x ₂≥k _fminx ₃ （12）

Wherein, f _PminFor minimum primary air flow, f _PmaxFor maximum primary air flow, f _SminFor minimum secondary air flow, f _SmaxFor maximum secondary air quantity, t _BminFor minimum operation bed temperature, t _BmaxFor the highest operation bed temperature, t _PminFor minimum exhaust gas temperature, k _FminFor minimum wind load ratio;

2.2) if (8)～(12) formula is all set up, judge that default performance variable is as feasible, otherwise judge that default performance variable is as infeasible;

3) find optimum performance variable, adopt following process to complete:

3.1) produce a random point X (x by (13), (14) formula take in the two dimensional surface that primary air flow, secondary air flow be reference axis ₁, x ₂):

x ₁=f _pmin+r ₁(f _pmax-f _pmin) （13）

x ₂=f _smin+r ₂(f _smax-f _smin) （14）

Wherein, r ₁, r ₂For (0,1) interval 2 interior pseudo random numbers;

3.2) by step 2) whether judging point X feasible, if some X is feasible, makes initial point X ⁽⁰⁾=X, otherwise go to step 3.1) produce new random point, until the random point X produced is feasible;

3.3) produce k by following formula _dIndividual random units vector:

e _j=[sin(2πq _j),cos(2πq _j)]，（j=1,2,...k _d） （15）

Wherein, k _dFor random units vector number, q _jFor (0,1) interval j interior pseudo random number, e _jBe j random units vector;

3.4) setting initial trial step-length α ₀

3.5) produce k by following formula _dIndividual random point:

X ^(j)=X ⁽⁰⁾+α ₀e _j，（j=1,2,...k _d） （16）

Wherein, α ₀For test step-length, X ^(j)Be j random point unit vector number;

3.6) by step 2) judgement k _dIndividual random point X ^(j)Whether feasible, feasible random point is predicted to its total energy loss f (X by step 1) ^(j)), the total energy loss of each feasible random point relatively, select the feasible random point of total energy loss minimum, is designated as X ^(L)

3.7) comparison f (X ^(L)) and f (X ⁽⁰⁾), if f is (X ^(L))<f (X ⁽⁰⁾), make S=X ^(L)-X ⁽⁰⁾Go to step 3.9), otherwise get

Return to step 3.5) regenerate k _dIndividual random point;

3.8) if α ₀<1 * 10 ^-10, still can not find an X ^(L)Make f (X ^(L))<f (X ⁽⁰⁾), go to step 3.11);

3.9) make S=1.2S;

3.10) comparison f (X ^(L)) and f (X ^(L)+ S), if f is (X ^(L)+ S)<f (X ^(L)), make X ^(L)=X ^(L)+ S, return to step 3.9), otherwise make X ⁽⁰⁾=X ^(L), return to step 3.3) and carry out next step optimizing;

3.11) X ⁽⁰⁾Be optimum point, the component that it is corresponding

Be optimum primary air flow and optimum secondary air flow;

Described method also comprises: in described step 3), read parameters from control station, and optimum primary air flow, Secondary Air value are passed to control station shown, so that control station staff, according to suggestion for operation, the adjusting operation condition, reduce the boiler energy loss in time, improves boiler operating efficiency.

Images