CN103488089A - System and method for controlling emission of noxious substances of pesticide waste liquid incinerator to reach standards in self-adaptation mode - Google Patents

Abstract

The invention discloses a system and method for controlling emission of noxious substances of a pesticide waste liquid incinerator to reach standards in a self-adaptation mode. The system comprises the incinerator, an intelligent instrument, a DCS, a data interface and an upper computer. The DCS comprises a control station and a database. The intelligent instrument used for measuring easily-measured variables is connected with the DCS. The DCS is connected with the upper computer through the data interface. The upper computer conducts standardized preprocessing on a training sample. A fuzzy neural network is adopted to establish a regression model, optimum optimization is carried out on linear parameters in the fuzzy neural network by introducing a support vector machine, the problem of parameter setting of the fuzzy neural network is solved, and meanwhile self-adaptation adjustment is carried out on the structure of the whole fuzzy neural network according to changes of the training sample. The upper computer further has the model updating function and the result displaying function. The system and method have the advantages of being capable of measuring COD in an online mode, effectively monitoring whether the COD exceeds the standards or not, controlling the emission of the COD to reach the standards, being strong in anti-noise capacity, optimizing parameters in an online mode, adjusting the structure of the system in the self-adaptation mode and the like.

Description

Adaptive pesticide waste liquid incinerator hazardous emission control system up to standard and method

Technical field

The present invention relates to the pesticide producing field, relate in particular to a kind of adaptive pesticide waste liquid incinerator hazardous emission control system up to standard and method.

Background technology

China is pesticide producing and use big country, and pesticide producing enterprise has reached 4100 left and right, and its Central Plains medicine manufacturing enterprise is family more than 500, and national Ministry of Agriculture statistics shows that 1～November in 2008, the agricultural chemicals total production reached 171.1 ten thousand tons.The irrationality of China's pesticide species structure has more strengthened the difficulty of environmental improvement.According to incompletely statistics, the waste water of the annual discharge of national pesticide industry is about 1,500,000,000 tons.Wherein, process and up to standard only account for processed 1%.Burning method be process at present agricultural chemicals raffinate and waste residue the most effectively, thoroughly, the most general method of application.After burning, the chemical oxygen consumption (COC) (COD) of waste water is the most important index that pesticide waste liquid burns hazardous emission, but it can't on-line measurement, and off-line measurement once needs four or five hours, can't reflect in time working conditions change and instruct actual production.Therefore, in actual burning process, the COD severe overweight.

At first nineteen sixty-five U.S. mathematician L.Zadeh has proposed the concept of Fuzzy set.Fuzzy logic, in the mode of its problem closer to daily people and meaning of one's words statement, starts to replace adhering to the classical logic that all things can mean with the binary item subsequently.1987, Bart Kosko took the lead in fuzzy theory and neural network combination have been carried out to comparatively systematic research.In time after this, theoretical and the application of fuzzy neural network has obtained development at full speed, the perfect of fuzzy neural theory not only accelerated in the research of the proposition of various new fuzzy neural network models and the learning algorithm adapted thereof, and also obtained in practice application very widely.But simultaneously structure of fuzzy neural network determine the problem the same with neural network that also run into, it is manually definite that structural parameters need the operative employee to rely on own operating experience.

Support vector machine, by Vapnik, in 1998, introduced, by using structural risk minimization in statistical theory study but not general experience structure Method for minimization, original optimal classification face problem is converted into to the optimization problem of its antithesis, thereby there is good Generalization Ability, be widely used in pattern-recognition, matching and classification problem.In this programme, support vector machine is used to the parameter in the Optimization of Fuzzy neural network model.

Summary of the invention

Can't on-line measurement in order to overcome existing incinerator process COD, the deficiency of COD severe overweight, the invention provides a kind of adaptive pesticide waste liquid incinerator hazardous emission control system up to standard and method, whether it has on-line measurement COD, effectively monitor COD exceeds standard, controls the advantages such as COD emission compliance, noise resisting ability are strong, on-line optimization parameter, self-adapted adjustment system structure.

The technical solution adopted for the present invention to solve the technical problems is:

Adaptive pesticide waste liquid incinerator hazardous emission control system up to standard, comprise incinerator, intelligent instrument, DCS system, data-interface and host computer, and described DCS system comprises control station and database; Described field intelligent instrument is connected with the DCS system, and described DCS system is connected with host computer, and described host computer comprises:

Data preprocessing module, for carrying out pre-service from the model training sample of DCS database input, the average that makes training sample is 0, and variance is 1, and this processing adopts following formula process to complete:

Computation of mean values: $\stackrel{\‾}{\mathrm{TX}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{\mathrm{TX}}_i---\left(1\right)$

Calculate variance: ${\mathrm{\σ}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}({\mathrm{TX}}_i-\stackrel{\‾}{\mathrm{TX}})---\left(2\right)$

Standardization: $X=\frac{\mathrm{TX}-\stackrel{\‾}{\mathrm{TX}}}{{\mathrm{\σ}}_x}---\left(3\right)$

Wherein, TX _ibe i training sample,, be the data of the production that gathers from the DCS database key variables, chemical oxygen consumption (COC) (COD) when normal and the performance variable while making accordingly the COD emission compliance, N is number of training,

for the average of training sample, X is the training sample after standardization.σ _xthe standard deviation that means training sample, σ ² _xthe variance that means training sample.The fuzzy neural network module, to pass the input variable of coming from data preprocessing module, carry out fuzzy reasoning and set up fuzzy rule.Carry out fuzzy classification to from data preprocessing module, passing the pretreated training sample X of process come, obtain center and the width of each fuzzy clustering in fuzzy rule base.If the training sample X after p standardization _p=[X _p1..., X _pn], wherein n is the number of input variable.

If fuzzy neural network has R fuzzy rule, in order to try to achieve each fuzzy rule for training sample X _peach input variable X _pj, j=1 ..., n, following obfuscation equation will be obtained its degree of membership to i fuzzy rule:

$M_{\mathrm{ij}}=\exp \{-\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\σ}}_{\mathrm{ij}}^2}\}---\left(4\right)$

M wherein _ijand σ _ijmean respectively center and the width of j Gauss's member function of i fuzzy rule, tried to achieve by fuzzy clustering.

If training sample X _pfitness to fuzzy rule i is μ ⁽ⁱ⁾(X _p), μ ⁽ⁱ⁾(X _p) large I by following formula, determined:

${\mathrm{\μ}}^{\left(i\right)}\left(X_p\right)=\underset{j=1}{\overset{n}{\mathrm{\Π}}}{M}_{\mathrm{ij}}\left(X_p\right)=\exp \{-\underset{j=1}{\overset{n}{\mathrm{\Σ}}}\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\σ}}_{\mathrm{ij}}^2}\}---\left(5\right)$

After trying to achieve the input training sample fitness regular for each, fuzzy neural network is exported and is derived to obtain last analytic solution fuzzy rule.In structure of fuzzy neural network commonly used, the process that each fuzzy rule is derived can be expressed as: at first try to achieve the linear sum of products of all input variables in training sample, then use this linear sum of products and regular relevance grade μ ⁽ⁱ⁾(X _p) multiply each other, obtain the output of every final fuzzy rule.The derivation output of fuzzy rule i can be expressed as follows:

$f^{\left(i\right)}={\mathrm{\μ}}^{\left(i\right)}\left(X_p\right)\×(\underset{j=1}{\overset{n}{\mathrm{\Σ}}}{a}_{\mathrm{ij}}\×X_{\mathrm{pj}}+a_{i0})---\left(6\right)$

${\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\Σ}}}{f}^{\left(i\right)}+b=\underset{i=1}{\overset{R}{\mathrm{\Σ}}}[{\mathrm{\μ}}^{\left(i\right)}\left(X_p\right)\×(\underset{j=1}{\overset{n}{\mathrm{\Σ}}}{a}_{\mathrm{ij}}\×X_{\mathrm{pj}}+a_{i0})]+b---\left(7\right)$

In formula, f ⁽ⁱ⁾be the output of i bar fuzzy rule,

the prediction output of fuzzy neural network model to p training sample, a _ij, j=1 ..., n is the linear coefficient of j variable in i bar fuzzy rule, a _i0be the constant term of the linear sum of products of input variable in i bar fuzzy rule, b is the output offset amount.

Support vector machine is optimized module, in formula (7), the definite of parameter in the linear sum of products of input variable is a subject matter of using during fuzzy neural network is used, here we adopt original fuzzy rule derivation output form are converted to the support vector machine optimization problem, re-use support vector machine and carry out linear optimization, transfer process is as follows:

$\begin{array}{c}{\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\Σ}}}{f}^{\left(i\right)}+b\\ =\underset{i=1}{\overset{R}{\mathrm{\Σ}}}[{\mathrm{\μ}}^{\left(i\right)}\left(X_p\right)\×(\underset{j=1}{\overset{n}{\mathrm{\Σ}}}{a}_{\mathrm{ij}}\×X_{\mathrm{pj}}+a_{i0})]+b\\ =\underset{i=1}{\overset{R}{\mathrm{\Σ}}}\underset{j=0}{\overset{n}{\mathrm{\Σ}}}{a}_{\mathrm{ij}}\×{\mathrm{\μ}}^{\left(i\right)}\left(X_p\right)\×X_{\mathrm{pj}}+b\end{array}---\left(8\right)$

X wherein _p0for constant term and be constantly equal to 1.Order

$\stackrel{\→}{\mathrm{\φ}}\left(X_p\right)=[{\mathrm{\μ}}^{\left(1\right)}\×X_{p0},...,{\mathrm{\μ}}^{\left(1\right)}\×X_{\mathrm{pn}},......,{\mathrm{\μ}}^{\left(R\right)}\×X_{p0},...,{\mathrm{\μ}}^{\left(R\right)}\×X_{\mathrm{pn}}]---\left(9\right)$

Wherein, the reformulations that means former training sample, be converted to original training sample as the above formula form, as the training sample of support vector machine:

$S=\{(\stackrel{\→}{\mathrm{\φ}}\left(X_1\right),y_1),(\stackrel{\→}{\mathrm{\φ}}\left(X_2\right),y_2),...,(\stackrel{\→}{\mathrm{\φ}}\left(X_N\right),y_N),\}---\left(10\right)$

Y wherein ₁..., y _nbe the target output of training sample, get S as new input training sample set, so original problem can be converted into following support vector machine primal-dual optimization problem:

$R(\mathrm{\ω},b)=\mathrm{\γ}\frac{1}{N}{\mathrm{\Σ}}_{p=1}^N{L}_{\mathrm{\ϵ}}(y_p,f\left(X_p\right))+\frac{1}{2}{\mathrm{\ω}}^T\mathrm{\ω}---\left(11\right)$

Y _pinput training sample X _ptarget output, f (X _p) be corresponding to X _pmodel output, L _ε(y _p, f (X _p)) be input training sample X _pcorresponding target output y _pwith model output f (X _p) once insensitive function when the error margin of optimization problem is ε.γ is the penalty factor of support vector machine, and R (ω, b) is the objective function of optimization problem, and N is number of training, L _ε(y _p, f (X _p)) expression formula is as follows:

Wherein ε is the error margin of optimization problem, next uses support vector machine to try to achieve the optimum derivation linear dimensions of fuzzy rule of fuzzy neural network and the forecast output of primal-dual optimization problem:

$a_{\mathrm{ij}}=\underset{k=1}{\overset{N}{\mathrm{\Σ}}}({\mathrm{\α}}_k^{*}-{\mathrm{\α}}_k){\mathrm{\μ}}^{\left(i\right)}{X}_{\mathrm{kj}}=\underset{k\∈\mathrm{SV}}{\overset{N}{\mathrm{\Σ}}}({\mathrm{\α}}_k^{*}-{\mathrm{\α}}_k){\mathrm{\μ}}^{\left(i\right)}{X}_{\mathrm{kj}},i=1,...,R;j=0,...,n---\left(13\right)$

${\hat{y}}_p=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k)<\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X\right),\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_k\right)>+b---\left(14\right)$

Wherein, respectively y _p-f (X _p) be greater than 0 and be less than 0 o'clock corresponding Lagrange multiplier,

p the COD predicted value and the performance variable value that makes the COD emission compliance that training sample is corresponding.

be corresponding to p training sample X _pmake the performance variable value of chemical oxygen demand (COD) discharge under.

Adaptive structure is optimized module, due to during the structural parameters in fuzzy neural network determine, is mainly to determine by artificial experience, once and definite, whole model structure can not adaptive optimization.This module increases threshold value μ by setting fuzzy rule _th-add, fuzzy rule importance reduces threshold value μ _th-d, fuzzy rule deletes threshold value μ _th-del, the structure to fuzzy neural network in the processing procedure to training sample is carried out the self-adaptation adjustment.In formula (5), fuzzy rule i is for p training sample X _p=[X _p1..., X _pn] fitness be μ ⁽ⁱ⁾(X _p), and in fuzzy rule, the fuzzy rule item of fitness value maximum is:

$I=\arg \underset{1\&le;i\&le;R}{\max }{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)---\left(15\right)$

Wherein

the item No. that means the fuzzy rule item of fitness value maximum,

If μ ^(I)<μ _th-add, fuzzy rule fitness maximal value is less than the fuzzy rule increase threshold value μ of setting _th-add, increase a new regulation.Center and the width of Gauss's member function of the fuzzy rule newly increased are:

$m_j^{\mathrm{new}}=X_{\mathrm{pj}},j=1,...,n---\left(16\right)$

${\mathrm{\&sigma;}}_j^{\mathrm{new}}=\mathrm{\&beta;}\&times;\frac{{\left|\right|X_{\mathrm{pj}}-m_{\mathrm{Ij}}\left|\right|}^2}{{\mathrm{\&sigma;}}_{\mathrm{Ij}}^2},j=1,...,n---\left(17\right)$

Wherein with

for center and the width of Gauss's member function of new fuzzy rule, constant beta>0 mean new fuzzy rule and the degree of overlapping between fuzzy rule I, generally the β value gets 1.2.

In order to prevent that the number of fuzzy rules purpose from constantly increasing, the deletion that adopts a kind of adaptive approach to decide fuzzy rule whether: if i bar fuzzy rule is for the adaptive value μ of p training sample ⁽ⁱ⁾(X _p) be less than fuzzy rule importance and reduce threshold value μ _th-d, its fuzzy rule importance just starts to reduce, otherwise increases, here the importance D of i bar fuzzy rule _imean; If the D of i bar fuzzy rule _ivalue is decreased to fuzzy rule and deletes threshold value μ in to the training sample training process _th-del, leave out i bar fuzzy rule.

The importance values D of each fuzzy rule _i, i=1 ..., the initial value value of R all is set to 1, its with the input training sample change procedure as the formula (18):

D wherein _ithe importance that means i bar fuzzy rule, constant τ value has determined the speed that fuzzy rule importance changes, and gets 1, μ here ⁽ⁱ⁾(X _p) mean the adaptive value of i bar fuzzy rule for p training sample, μ _th-dmean that fuzzy rule importance reduces threshold value.

Work as D _imeet D _i<μ _th-delthe time, μ here _th-delget 0.005, leave out i bar fuzzy rule.

As preferred a kind of scheme: described host computer also comprises: the discrimination model update module, for the sampling time interval by setting, collection site intelligent instrument signal, the actual measurement chemical oxygen consumption (COC) function predicted value obtained is compared, if relative error be greater than 10% or actual measurement COD data not up to standard, the new data up to standard of producing in the DCS database when normal is added to training sample data, Renewal model.

Further, described host computer also comprises: display module as a result, be used for the COD predicted value and make the performance variable value of COD emission compliance pass to the DCS system, and, at the control station procedure for displaying state of DCS, by DCS system and fieldbus, process status information is delivered to operator station simultaneously and is shown; Simultaneously, the DCS system, using the resulting performance variable value that makes the COD emission compliance as new performance variable setting value, automatically performs the operation of COD emission compliance.

Signal acquisition module, for the time interval of the each sampling according to setting, image data from database.

Further again, described key variables comprise the waste liquid flow that enters incinerator, enter the air mass flow of incinerator and enter the fuel flow rate of incinerator; Described performance variable comprises the air mass flow that enters incinerator and the fuel flow rate that enters incinerator.

The hazardous emission control method up to standard that adaptive pesticide waste liquid incinerator hazardous emission control system up to standard realizes, described control method specific implementation step is as follows::

1), to pesticide waste liquid incinerator hazardous emission process object, according to industrial analysis and Operations Analyst, determine key variables used, when from the DCS database, collection production is normal, the data of described variable, as the input matrix of training sample TX, gather corresponding COD and make the performance variable data of COD emission compliance as output matrix Y;

2), for carrying out pre-service from the model training sample of DCS database input, the average that makes training sample is 0, variance is 1, the following formula process of this processings employing completes:

Computation of mean values: $\stackrel{\&OverBar;}{\mathrm{TX}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{TX}}_i---\left(1\right)$

Calculate variance: ${\mathrm{\&sigma;}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{TX}}_i-\stackrel{\&OverBar;}{\mathrm{TX}})---\left(2\right)$

Standardization: $X=\frac{\mathrm{TX}-\stackrel{\&OverBar;}{\mathrm{TX}}}{{\mathrm{\&sigma;}}_x}---\left(3\right)$

Wherein, TX _ibe i training sample,, be the data of the production that gathers from the DCS database key variables, chemical oxygen consumption (COC) (COD) when normal and the performance variable while making accordingly the COD emission compliance, N is number of training,

for the average of training sample, X is the training sample after standardization.σ _xthe standard deviation that means training sample, σ ² _xthe variance that means training sample.

3), to pass the input variable come from data preprocessing module, carry out fuzzy reasoning and set up fuzzy rule.Carry out fuzzy classification to from data preprocessing module, passing the pretreated training sample X of process come, obtain center and the width of each fuzzy clustering in fuzzy rule base.If the training sample X after p standardization _p=[X _p1..., X _pn], wherein n is the number of input variable.

If fuzzy neural network has R fuzzy rule, in order to try to achieve each fuzzy rule for training sample X _peach input variable X _pj, j=1 ..., n, following obfuscation equation will be obtained its degree of membership to i fuzzy rule:

$M_{\mathrm{ij}}=\exp \{-\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(4\right)$

M wherein _ijand σ _ijmean respectively center and the width of j Gauss's member function of i fuzzy rule, tried to achieve by fuzzy clustering.

If training sample X _pfitness to fuzzy rule i is μ ⁽ⁱ⁾(X _p), μ ⁽ⁱ⁾(X _p) large I by following formula, determined:

${\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)=\underset{j=1}{\overset{n}{\mathrm{\&Pi;}}}{M}_{\mathrm{ij}}\left(X_p\right)=\exp \{-\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(5\right)$

After trying to achieve the input training sample fitness regular for each, fuzzy neural network is exported and is derived to obtain last analytic solution fuzzy rule.In structure of fuzzy neural network commonly used, the process that each fuzzy rule is derived can be expressed as: at first try to achieve the linear sum of products of all input variables in training sample, then use this linear sum of products and regular relevance grade μ ⁽ⁱ⁾(X _p) multiply each other, obtain the output of every final fuzzy rule.The derivation output of fuzzy rule i can be expressed as follows:

$f^{\left(i\right)}={\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})---\left(6\right)$

${\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b---\left(7\right)$

In formula, f ⁽ⁱ⁾be the output of i bar fuzzy rule,

the prediction output of fuzzy neural network model to p training sample, a _ij, j=1 ..., n is the linear coefficient of j variable in i bar fuzzy rule, a _i0be the constant term of the linear sum of products of input variable in i bar fuzzy rule, b is the output offset amount.

4), in formula (7), the definite of parameter in the linear sum of products of input variable is a subject matter of using during fuzzy neural network is used, here we adopt original fuzzy rule derivation output form are converted to the support vector machine optimization problem, re-use support vector machine and carry out linear optimization, transfer process is as follows:

$\begin{array}{c}{\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}\underset{j=0}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;X_{\mathrm{pj}}+b\end{array}---\left(8\right)$

X wherein _p0for constant term and be constantly equal to 1.Order

$\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_p\right)=[{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{\mathrm{pn}},......,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{\mathrm{pn}}]---\left(9\right)$

Wherein, the reformulations that means former training sample, be converted to original training sample as the above formula form, as the training sample of support vector machine:

$S=\{(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_1\right),y_1),(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_2\right),y_2),...,(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_N\right),y_N),\}---\left(10\right)$

Y wherein ₁..., y _nbe the target output of training sample, get S as new input training sample set, so original problem can be converted into following support vector machine primal-dual optimization problem:

$R(\mathrm{\&omega;},b)=\mathrm{\&gamma;}\frac{1}{N}{\mathrm{\&Sigma;}}_{p=1}^N{L}_{\mathrm{\&epsiv;}}(y_p,f\left(X_p\right))+\frac{1}{2}{\mathrm{\&omega;}}^T\mathrm{\&omega;}---\left(11\right)$

Y wherein _pinput training sample X _ptarget output, f (X _p) be corresponding to X _pmodel output, L _ε(y _p, f (X _p)) be input training sample X _pcorresponding target output y _pwith model output f (X _p) once insensitive function when the error margin of optimization problem is ε.γ is the penalty factor of support vector machine, and R (ω, b) is the objective function of optimization problem, and N is number of training, L _ε(y _p, f (X _p)) expression formula is as follows:

Wherein ε is the error margin of optimization problem, next uses support vector machine to try to achieve the optimum derivation linear dimensions of fuzzy rule of fuzzy neural network and the forecast output of primal-dual optimization problem:

$a_{\mathrm{ij}}=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}}=\underset{k\&Element;\mathrm{SV}}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}},i=1,...,R;j=0,...,n---\left(13\right)$

${\hat{y}}_p=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k)<\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X\right),\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_k\right)>+b---\left(14\right)$

Wherein

respectively y _p-f (X _p) be greater than 0 and be less than 0 o'clock corresponding Lagrange multiplier,

p the COD predicted value and the performance variable value that makes the COD emission compliance that training sample is corresponding.

5), set fuzzy rule and increase threshold value μ _th-add, fuzzy rule importance reduces threshold value μ _th-d, fuzzy rule deletes threshold value μ _th-del, the structure to fuzzy neural network in the processing procedure to training sample is carried out the self-adaptation adjustment.In formula (5), fuzzy rule i is for p training sample X _p=[x ₁..., x _n] fitness be μ ⁽ⁱ⁾(X _p), and in fuzzy rule, the fuzzy rule item of fitness value maximum is:

$I=\arg \underset{1\&le;i\&le;R}{\max }{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)---\left(15\right)$

Wherein

the item No. that means the fuzzy rule item of fitness value maximum,

If μ ^(I)<μ _th-add, fuzzy rule fitness maximal value is less than the fuzzy rule increase threshold value μ of setting _th-add, increase a new regulation.Center and the width of Gauss's member function of the fuzzy rule newly increased are:

$m_j^{\mathrm{new}}=X_{\mathrm{pj}},j=1,...,n---\left(16\right)$

${\mathrm{\&sigma;}}_j^{\mathrm{new}}=\mathrm{\&beta;}\&times;\frac{{\left|\right|X_{\mathrm{pj}}-m_{\mathrm{Ij}}\left|\right|}^2}{{\mathrm{\&sigma;}}_{\mathrm{Ij}}^2},j=1,...,n---\left(17\right)$

Wherein with for center and the width of Gauss's member function of new fuzzy rule, constant beta>0 mean new fuzzy rule and the degree of overlapping between fuzzy rule I, generally the β value gets 1.2.

In order to prevent that the number of fuzzy rules purpose from constantly increasing, the deletion that adopts a kind of adaptive approach to decide fuzzy rule whether: if i bar fuzzy rule is for the adaptive value μ of p training sample ⁽ⁱ⁾(X _p) be less than fuzzy rule importance and reduce threshold value μ _th-d, its fuzzy rule importance just starts to reduce, otherwise increases, here the importance D of i bar fuzzy rule _imean; If the D of i bar fuzzy rule _ivalue is decreased to fuzzy rule and deletes threshold value μ in to the training sample training process _th-del, leave out i bar fuzzy rule.

The importance values D of each fuzzy rule _i, i=1 ..., the initial value value of R all is set to 1, its with the input training sample change procedure as the formula (18):

D wherein _ithe importance that means i bar fuzzy rule, constant τ value has determined the speed that fuzzy rule importance changes, and gets 1, μ here ⁽ⁱ⁾(X _p) mean the adaptive value of i bar fuzzy rule for p training sample, μ _th-dmean that fuzzy rule importance reduces threshold value.

Work as D _imeet D _i<μ _th-delthe time, μ here _th-delget 0.005, leave out i bar fuzzy rule.

As preferred a kind of scheme: described method also comprises: 6) by the sampling time interval of setting, collection site intelligent instrument signal, the actual measurement chemical oxygen consumption (COC) function predicted value obtained is compared, if relative error be greater than 10% or actual measurement COD data not up to standard, the new data up to standard of producing in the DCS database when normal is added to training sample data, Renewal model.

Further, in described step 4), by COD predicted value and make the performance variable value of COD emission compliance pass to the DCS system, and, at the control station procedure for displaying state of DCS, by DCS system and fieldbus, process status information is delivered to operator station simultaneously and is shown; Simultaneously, the DCS system, using the resulting performance variable value that makes the COD emission compliance as new performance variable setting value, automatically performs the operation of COD emission compliance.

Further again, described key variables comprise the waste liquid flow that enters incinerator, and the air mass flow that enters incinerator enters the fuel flow rate of incinerator; Described performance variable comprises the air mass flow that enters incinerator and the fuel flow rate that enters incinerator.

Technical conceive of the present invention is: the invention provides a kind of adaptive pesticide waste liquid incinerator hazardous emission control system up to standard and method, search out the performance variable value that makes chemical oxygen demand (COD) discharge up to standard.

Beneficial effect of the present invention is mainly manifested in: the online soft sensor model of 1, having set up quantitative relationship between system core variable and chemical oxygen demand (COD) discharge; 2, find rapidly the operating conditions that makes chemical oxygen demand (COD) discharge up to standard.

The accompanying drawing explanation

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

Fig. 2 is the functional structure chart of host computer proposed by the invention.

Embodiment

Below in conjunction with accompanying drawing, the invention will be further described.The embodiment of the present invention is used for the present invention that explains, rather than limits the invention, and in the protection domain of spirit of the present invention and claim, any modification and change that the present invention is made, all fall into protection scope of the present invention.

Embodiment 1

With reference to Fig. 1, Fig. 2, adaptive pesticide waste liquid incinerator hazardous emission control system up to standard, comprise the field intelligent instrument 2, DCS system and the host computer 6 that are connected with incinerator 1, described DCS system comprises data-interface 3, control station 5 and database 4, described field intelligent instrument 2 is connected with data-interface 3, described data-interface is connected with control station 5, database 4 and host computer 6, and described host computer 6 comprises:

Data preprocessing module, for carrying out pre-service from the model training sample of DCS database input, the average that makes training sample is 0, and variance is 1, and this processing adopts following formula process to complete:

Computation of mean values: $\stackrel{\&OverBar;}{\mathrm{TX}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{TX}}_i---\left(1\right)$

Calculate variance: ${\mathrm{\&sigma;}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{TX}}_i-\stackrel{\&OverBar;}{\mathrm{TX}})---\left(2\right)$

Standardization: $X=\frac{\mathrm{TX}-\stackrel{\&OverBar;}{\mathrm{TX}}}{{\mathrm{\&sigma;}}_x}---\left(3\right)$

Wherein, TX _ibe i training sample,, be the data of the production that gathers from the DCS database key variables, chemical oxygen consumption (COC) (COD) when normal and the performance variable while making accordingly the COD emission compliance, N is number of training,

for the average of training sample, X is the training sample after standardization.σ _xthe standard deviation that means training sample, σ ² _xthe variance that means training sample.The fuzzy neural network module, to pass the input variable of coming from data preprocessing module, carry out fuzzy reasoning and set up fuzzy rule.Carry out fuzzy classification to from data preprocessing module, passing the pretreated training sample X of process come, obtain center and the width of each fuzzy clustering in fuzzy rule base.If the training sample X after p standardization _p=[X _p1..., X _pn], wherein n is the number of input variable.

If fuzzy neural network has R fuzzy rule, in order to try to achieve each fuzzy rule for training sample X _peach input variable X _pj, j=1 ..., n, following obfuscation equation will be obtained its degree of membership to i fuzzy rule:

$M_{\mathrm{ij}}=\exp \{-\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(4\right)$

M wherein _ijand σ _ijmean respectively center and the width of j Gauss's member function of i fuzzy rule, tried to achieve by fuzzy clustering.

If training sample X _pfitness to fuzzy rule i is μ ⁽ⁱ⁾(X _p), μ ⁽ⁱ⁾(X _p) large I by following formula, determined:

${\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)=\underset{j=1}{\overset{n}{\mathrm{\&Pi;}}}{M}_{\mathrm{ij}}\left(X_p\right)=\exp \{-\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(5\right)$

After trying to achieve the input training sample fitness regular for each, fuzzy neural network is exported and is derived to obtain last analytic solution fuzzy rule.In structure of fuzzy neural network commonly used, the process that each fuzzy rule is derived can be expressed as: at first try to achieve the linear sum of products of all input variables in training sample, then use this linear sum of products and regular relevance grade μ ⁽ⁱ⁾(X _p) multiply each other, obtain the output of every final fuzzy rule.The derivation output of fuzzy rule i can be expressed as follows:

$f^{\left(i\right)}={\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})---\left(6\right)$

${\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b---\left(7\right)$

In formula, f ⁽ⁱ⁾be the output of i bar fuzzy rule,

the prediction output of fuzzy neural network model to p training sample, a _ij, j=1 ..., n is the linear coefficient of j variable in i bar fuzzy rule, a _i0be the constant term of the linear sum of products of input variable in i bar fuzzy rule, b is the output offset amount.

Support vector machine is optimized module, in formula (7), the definite of parameter in the linear sum of products of input variable is a subject matter of using during fuzzy neural network is used, here we adopt original fuzzy rule derivation output form are converted to the support vector machine optimization problem, re-use support vector machine and carry out linear optimization, transfer process is as follows:

$\begin{array}{c}{\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}\underset{j=0}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;X_{\mathrm{pj}}+b\end{array}---\left(8\right)$

X wherein _p0for constant term and be constantly equal to 1.Order

$\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_p\right)=[{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{\mathrm{pn}},......,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{\mathrm{pn}}]---\left(9\right)$

Wherein, the reformulations that means former training sample, be converted to original training sample as the above formula form, as the training sample of support vector machine:

$S=\{(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_1\right),y_1),(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_2\right),y_2),...,(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_N\right),y_N),\}---\left(10\right)$

Y wherein ₁..., y _nbe the target output of training sample, get S as new input training sample set, so original problem can be converted into following support vector machine primal-dual optimization problem:

$R(\mathrm{\&omega;},b)=\mathrm{\&gamma;}\frac{1}{N}{\mathrm{\&Sigma;}}_{p=1}^N{L}_{\mathrm{\&epsiv;}}(y_p,f\left(X_p\right))+\frac{1}{2}{\mathrm{\&omega;}}^T\mathrm{\&omega;}---\left(11\right)$

Y _pinput training sample X _ptarget output, f (X _p) be corresponding to X _pmodel output, L _ε(y _p, f (X _p)) be input training sample X _pcorresponding target output y _pwith model output f (X _p) once insensitive function when the error margin of optimization problem is ε.γ is the penalty factor of support vector machine, and R (ω, b) is the objective function of optimization problem, and N is number of training, L _ε(y _p, f (X _p)) expression formula is as follows:

Wherein ε is the error margin of optimization problem, next uses support vector machine to try to achieve the optimum derivation linear dimensions of fuzzy rule of fuzzy neural network and the forecast output of primal-dual optimization problem:

$a_{\mathrm{ij}}=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}}=\underset{k\&Element;\mathrm{SV}}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}},i=1,...,R;j=0,...,n---\left(13\right)$

${\hat{y}}_p=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k)<\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X\right),\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_k\right)>+b---\left(14\right)$

Wherein

respectively y _p-f (X _p) be greater than 0 and be less than 0 o'clock corresponding Lagrange multiplier,

p the COD predicted value and the performance variable value that makes the COD emission compliance that training sample is corresponding.

Adaptive structure is optimized module, due to during the structural parameters in fuzzy neural network determine, is mainly to determine by artificial experience, once and definite, whole model structure can not adaptive optimization.This module increases threshold value μ by setting fuzzy rule _th-add, fuzzy rule importance reduces threshold value μ _th-d, fuzzy rule deletes threshold value μ _th-del, the structure to fuzzy neural network in the processing procedure to training sample is carried out the self-adaptation adjustment.In formula (5), fuzzy rule i is for p training sample X _p=[X _p1..., X _pn] fitness be μ ⁽ⁱ⁾(X _p), and in fuzzy rule, the fuzzy rule item of fitness value maximum is:

$I=\arg \underset{1\&le;i\&le;R}{\max }{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)---\left(15\right)$

Wherein

the item No. that means the fuzzy rule item of fitness value maximum,

If μ ^(I)<μ _th-add, fuzzy rule fitness maximal value is less than the fuzzy rule increase threshold value μ of setting _th-add, increase a new regulation.Center and the width of Gauss's member function of the fuzzy rule newly increased are:

$m_j^{\mathrm{new}}=X_{\mathrm{pj}},j=1,...,n---\left(16\right)$

${\mathrm{\&sigma;}}_j^{\mathrm{new}}=\mathrm{\&beta;}\&times;\frac{{\left|\right|X_{\mathrm{pj}}-m_{\mathrm{Ij}}\left|\right|}^2}{{\mathrm{\&sigma;}}_{\mathrm{Ij}}^2},j=1,...,n---\left(17\right)$

Wherein

with

for center and the width of Gauss's member function of new fuzzy rule, constant beta>0 mean new fuzzy rule and the degree of overlapping between fuzzy rule I, generally the β value gets 1.2.

In order to prevent that the number of fuzzy rules purpose from constantly increasing, the deletion that adopts a kind of adaptive approach to decide fuzzy rule whether: if i bar fuzzy rule is for the adaptive value μ of p training sample ⁽ⁱ⁾(X _p) be less than fuzzy rule importance and reduce threshold value μ _th-d, its fuzzy rule importance just starts to reduce, otherwise increases, here the importance D of i bar fuzzy rule _imean; If the D of i bar fuzzy rule _ivalue is decreased to fuzzy rule and deletes threshold value μ in to the training sample training process _th-del, leave out i bar fuzzy rule.

The importance values D of each fuzzy rule _i, i=1 ..., the initial value value of R all is set to 1, its with the input training sample change procedure as the formula (18):

D wherein _ithe importance that means i bar fuzzy rule, constant τ value has determined the speed that fuzzy rule importance changes, and gets 1, μ here ⁽ⁱ⁾(X _p) mean the adaptive value of i bar fuzzy rule for p training sample, μ _th-dmean that fuzzy rule importance reduces threshold value.

Work as D _imeet D _i<μ _th-delthe time, μ here _th-delget 0.005, leave out i bar fuzzy rule.

Described host computer 6 also comprises: signal acquisition module 11, for the time interval of the each sampling according to setting, image data from database;

Described host computer 6 also comprises: discrimination model update module 12, by the sampling time interval of setting, collection site intelligent instrument signal, the actual measurement COD function predicted value obtained is compared, if relative error be greater than 10% or actual measurement COD data not up to standard, the new data up to standard of producing in the DCS database when normal is added to training sample data, Renewal model.

Described system also comprises the DCS system, and described DCS system consists of data-interface 3, control station 5, database 4; Intelligent instrument 2, DCS system, host computer 6 are connected successively by fieldbus; Host computer 6 also comprises display module 10 as a result, be used for the COD predicted value and make the performance variable value of COD emission compliance pass to the DCS system, and, at the control station procedure for displaying state of DCS, by DCS system and fieldbus, process status information is delivered to operator station simultaneously and is shown; Simultaneously, the DCS system, using the resulting performance variable value that makes the COD emission compliance as new performance variable setting value, automatically performs the operation of COD emission compliance.

When the liquid waste incineration process has been furnished with the DCS system, the real-time and historical data base of the detection of sample real-time dynamic data, memory by using DCS system, obtain the COD predicted value and the function of the performance variable value of COD emission compliance mainly completed on host computer.

When the liquid waste incineration process is not equipped with the DCS system, adopted data memory substitutes the data storage function of the real-time and historical data base of DCS system, and one of the DCS system that do not rely on that will obtain the COD predicted value and the function system of the performance variable value of COD emission compliance is manufactured comprising I/O element, data-carrier store, program storage, arithmetical unit, several large members of display module complete SOC (system on a chip) independently, in the situation that no matter whether burning process is equipped with DCS, can both independently use, more be of value to and promoting the use of.

Embodiment 2

With reference to Fig. 1, Fig. 2, adaptive pesticide waste liquid incinerator hazardous emission control method up to standard, described control method specific implementation step is as follows:

1), to pesticide waste liquid incinerator hazardous emission process object, according to industrial analysis and Operations Analyst, determine key variables used, when from the DCS database, collection production is normal, the data of described variable, as the input matrix of training sample TX, gather corresponding COD and make the performance variable data of COD emission compliance as output matrix Y;

2), for carrying out pre-service from the model training sample of DCS database input, the average that makes training sample is 0, variance is 1, the following formula process of this processings employing completes:

Computation of mean values: $\stackrel{\&OverBar;}{\mathrm{TX}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{TX}}_i---\left(1\right)$

Calculate variance: ${\mathrm{\&sigma;}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{TX}}_i-\stackrel{\&OverBar;}{\mathrm{TX}})---\left(2\right)$

Standardization: $X=\frac{\mathrm{TX}-\stackrel{\&OverBar;}{\mathrm{TX}}}{{\mathrm{\&sigma;}}_x}---\left(3\right)$

Wherein, TX _ibe i training sample,, be the data of the production that gathers from the DCS database key variables, chemical oxygen consumption (COC) (COD) when normal and the performance variable while making accordingly the COD emission compliance, N is number of training,

for the average of training sample, X is the training sample after standardization.σ _xthe standard deviation that means training sample, σ ² _xthe variance that means training sample.

3), to pass the input variable come from data preprocessing module, carry out fuzzy reasoning and set up fuzzy rule.Carry out fuzzy classification to from data preprocessing module, passing the pretreated training sample X of process come, obtain center and the width of each fuzzy clustering in fuzzy rule base.If the training sample X after p standardization _p=[X _p1..., X _pn], wherein n is the number of input variable.

If fuzzy neural network has R fuzzy rule, in order to try to achieve each fuzzy rule for training sample X _peach input variable X _pj, j=1 ..., n, following obfuscation equation will be obtained its degree of membership to i fuzzy rule:

$M_{\mathrm{ij}}=\exp \{-\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(4\right)$

M wherein _ijand σ _ijmean respectively center and the width of j Gauss's member function of i fuzzy rule, tried to achieve by fuzzy clustering.

If training sample X _pfitness to fuzzy rule i is μ ⁽ⁱ⁾(X _p), μ ⁽ⁱ⁾(X _p) large I by following formula, determined:

${\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)=\underset{j=1}{\overset{n}{\mathrm{\&Pi;}}}{M}_{\mathrm{ij}}\left(X_p\right)=\exp \{-\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(5\right)$

After trying to achieve the input training sample fitness regular for each, fuzzy neural network is exported and is derived to obtain last analytic solution fuzzy rule.In structure of fuzzy neural network commonly used, the process that each fuzzy rule is derived can be expressed as: at first try to achieve the linear sum of products of all input variables in training sample, then use this linear sum of products and regular relevance grade μ ⁽ⁱ⁾(X _p) multiply each other, obtain the output of every final fuzzy rule.The derivation output of fuzzy rule i can be expressed as follows:

$f^{\left(i\right)}={\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})---\left(6\right)$

${\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b---\left(7\right)$

In formula, f ⁽ⁱ⁾be the output of i bar fuzzy rule,

the prediction output of fuzzy neural network model to p training sample, a _ij, j=1 ..., n is the linear coefficient of j variable in i bar fuzzy rule, a _i0be the constant term of the linear sum of products of input variable in i bar fuzzy rule, b is the output offset amount.

4), in formula (7), the definite of parameter in the linear sum of products of input variable is a subject matter of using during fuzzy neural network is used, here we adopt original fuzzy rule derivation output form are converted to the support vector machine optimization problem, re-use support vector machine and carry out linear optimization, transfer process is as follows:

$\begin{array}{c}{\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}\underset{j=0}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;X_{\mathrm{pj}}+b\end{array}---\left(8\right)$

X wherein _p0be constantly equal to 1.Order

$\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_p\right)=[{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{\mathrm{pn}},......,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{\mathrm{pn}}]---\left(9\right)$

Wherein,

the reformulations that means former training sample, be converted to original training sample as the above formula form, as the training sample of support vector machine:

$\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_p\right)=[{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{\mathrm{pn}},......,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{\mathrm{pn}}]---\left(9\right)$

Y wherein ₁..., y _nbe the target output of training sample, get S as new input training sample set, so original problem can be converted into following support vector machine primal-dual optimization problem:

$R(\mathrm{\&omega;},b)=\mathrm{\&gamma;}\frac{1}{N}{\mathrm{\&Sigma;}}_{p=1}^N{L}_{\mathrm{\&epsiv;}}(y_p,f\left(X_p\right))+\frac{1}{2}{\mathrm{\&omega;}}^T\mathrm{\&omega;}---\left(11\right)$

Y _pinput training sample X _ptarget output, f (X _p) be corresponding to X _pmodel output, L _ε(y _p, f (X _p)) be input training sample X _pcorresponding target output y _pwith model output f (X _p) once insensitive function when the error margin of optimization problem is ε.γ is the penalty factor of support vector machine, and R (ω, b) is the objective function of optimization problem, and N is number of training, L _ε(y _p, f (X _p)) expression formula is as follows:

Wherein ε is the error margin of optimization problem, next uses support vector machine to try to achieve the optimum derivation linear dimensions of fuzzy rule of fuzzy neural network and the forecast output of primal-dual optimization problem:

$a_{\mathrm{ij}}=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}}=\underset{k\&Element;\mathrm{SV}}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}},i=1,...,R;j=0,...,n---\left(13\right)$

${\hat{y}}_p=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k)<\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X\right),\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_k\right)>+b---\left(14\right)$

Wherein respectively y _p-f (X _p) be greater than 0 and be less than 0 o'clock corresponding Lagrange multiplier,

p the COD predicted value and the performance variable value that makes the COD emission compliance that training sample is corresponding.

5), set fuzzy rule and increase threshold value μ _th-add, fuzzy rule importance reduces threshold value μ _th-d, fuzzy rule deletes threshold value μ _th-del, the structure to fuzzy neural network in the processing procedure to training sample is carried out the self-adaptation adjustment.In formula (5), fuzzy rule i is for p training sample X _p=[x ₁..., x _n] fitness be μ ⁽ⁱ⁾(X _p), and in fuzzy rule, the fuzzy rule item of fitness value maximum is:

$I=\arg \underset{1\&le;i\&le;R}{\max }{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)---\left(15\right)$

Wherein

the item No. that means the fuzzy rule item of fitness value maximum,

If μ ^(I)<μ _th-add, fuzzy rule fitness maximal value is less than the fuzzy rule increase threshold value μ of setting _th-add, increase a new regulation.Center and the width of Gauss's member function of the fuzzy rule newly increased are:

$m_j^{\mathrm{new}}=X_{\mathrm{pj}},j=1,...,n---\left(16\right)$

${\mathrm{\&sigma;}}_j^{\mathrm{new}}=\mathrm{\&beta;}\&times;\frac{{\left|\right|X_{\mathrm{pj}}-m_{\mathrm{Ij}}\left|\right|}^2}{{\mathrm{\&sigma;}}_{\mathrm{Ij}}^2},j=1,...,n---\left(17\right)$

Wherein with

for center and the width of Gauss's member function of new fuzzy rule, constant beta>0 mean new fuzzy rule and the degree of overlapping between fuzzy rule I, generally the β value gets 1.2.

In order to prevent that the number of fuzzy rules purpose from constantly increasing, the deletion that adopts a kind of adaptive approach to decide fuzzy rule whether: if i bar fuzzy rule is for the adaptive value μ of p training sample ⁽ⁱ⁾(X _p) be less than fuzzy rule importance and reduce threshold value μ _th-d, its fuzzy rule importance just starts to reduce, otherwise increases, here the importance D of i bar fuzzy rule _imean; If the D of i bar fuzzy rule _ivalue is decreased to fuzzy rule and deletes threshold value μ in to the training sample training process _th-del, leave out i bar fuzzy rule.

The importance values D of each fuzzy rule _i, i=1 ..., the initial value value of R all is set to 1, its with the input training sample change procedure as the formula (18):

D wherein _ithe importance that means i bar fuzzy rule, constant τ value has determined the speed that fuzzy rule importance changes, and gets 1, μ here ⁽ⁱ⁾(X _p) mean the adaptive value of i bar fuzzy rule for p training sample, μ _th-dmean that fuzzy rule importance reduces threshold value.

Work as D _imeet D _i<μ _th-delthe time, μ here _th-delget 0.005, leave out i bar fuzzy rule.

6), by the sampling time interval of setting described method also comprises:, collection site intelligent instrument signal, the actual measurement COD function predicted value obtained is compared, if relative error be greater than 10% or actual measurement COD data not up to standard, the new data up to standard of producing in the DCS database when normal is added to training sample data, Renewal model.

7), in described step 4), by COD predicted value and make the performance variable value of COD emission compliance pass to the DCS system, and, at the control station procedure for displaying state of DCS, by DCS system and fieldbus, process status information is delivered to operator station simultaneously and is shown; Simultaneously, the DCS system, using the resulting performance variable value that makes the COD emission compliance as new performance variable setting value, automatically performs the operation of COD emission compliance.

Described key variables comprise the waste liquid flow that enters incinerator, and the air mass flow that enters incinerator enters the fuel flow rate of incinerator; Described performance variable comprises the air mass flow that enters incinerator and the fuel flow rate that enters incinerator.

Claims (2)

1. an adaptive pesticide waste liquid incinerator hazardous emission control system up to standard, comprise incinerator, intelligent instrument, DCS system, data-interface and host computer, and described DCS system comprises control station and database; Described field intelligent instrument is connected with the DCS system, and described DCS system is connected with host computer, it is characterized in that: described host computer comprises:

Data preprocessing module, for carrying out pre-service from the model training sample of DCS database input, the average that makes training sample is 0, and variance is 1, and this processing adopts following formula process to complete:

Computation of mean values: $\stackrel{\&OverBar;}{\mathrm{TX}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{TX}}_i---\left(1\right)$

Calculate variance: ${\mathrm{\&sigma;}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{TX}}_i-\stackrel{\&OverBar;}{\mathrm{TX}})---\left(2\right)$

Standardization: $X=\frac{\mathrm{TX}-\stackrel{\&OverBar;}{\mathrm{TX}}}{{\mathrm{\&sigma;}}_x}---\left(3\right)$

Wherein, TX _ibe i training sample,, be the data of the production that gathers from the DCS database key variables, chemical oxygen consumption (COC) (COD) when normal and the performance variable while making accordingly the COD emission compliance, N is number of training,

for the average of training sample, X is the training sample after standardization.σ _xthe standard deviation that means training sample, σ ² _xthe variance that means training sample.The fuzzy neural network module, to pass the input variable of coming from data preprocessing module, carry out fuzzy reasoning and set up fuzzy rule.Carry out fuzzy classification to from data preprocessing module, passing the pretreated training sample X of process come, obtain center and the width of each fuzzy clustering in fuzzy rule base.If the training sample X after p standardization _p=[X _p1..., X _pn], wherein n is the number of input variable.

If fuzzy neural network has R fuzzy rule, in order to try to achieve each fuzzy rule for training sample X _peach input variable X _pj, j=1 ..., n, following obfuscation equation will be obtained its degree of membership to i fuzzy rule:

$M_{\mathrm{ij}}=\exp \{-\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(4\right)$

M wherein _ijand σ _ijmean respectively center and the width of j Gauss's member function of i fuzzy rule, tried to achieve by fuzzy clustering.

If training sample X _pfitness to fuzzy rule i is μ ⁽ⁱ⁾(X _p), μ ⁽ⁱ⁾(X _p) large I by following formula, determined:

${\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)=\underset{j=1}{\overset{n}{\mathrm{\&Pi;}}}{M}_{\mathrm{ij}}\left(X_p\right)=\exp \{-\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(5\right)$

After trying to achieve the input training sample fitness regular for each, fuzzy neural network is exported and is derived to obtain last analytic solution fuzzy rule.In structure of fuzzy neural network commonly used, the process that each fuzzy rule is derived can be expressed as: at first try to achieve the linear sum of products of all input variables in training sample, then use this linear sum of products and regular relevance grade μ ⁱ(X _p) multiply each other, obtain the output of every final fuzzy rule.The derivation output of fuzzy rule i can be expressed as follows:

$f^{\left(i\right)}={\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})---\left(6\right)$

${\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b---\left(7\right)$

In formula, f ⁽ⁱ⁾be the output of i bar fuzzy rule,

the prediction output of fuzzy neural network model to p training sample, a _ij, j=1 ..., n is the linear coefficient of j variable in i bar fuzzy rule, a _i0be the constant term of the linear sum of products of input variable in i bar fuzzy rule, b is the output offset amount.

Support vector machine is optimized module, in formula (7), the definite of parameter in the linear sum of products of input variable is a subject matter of using during fuzzy neural network is used, here we adopt original fuzzy rule derivation output form are converted to the support vector machine optimization problem, re-use support vector machine and carry out linear optimization, transfer process is as follows:

$\begin{array}{c}{\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}\underset{j=0}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;X_{\mathrm{pj}}+b\end{array}---\left(8\right)$

X wherein _p0for constant term and be constantly equal to 1.Order

$\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_p\right)=[{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{\mathrm{pn}},......,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{\mathrm{pn}}]---\left(9\right)$

Wherein,

the reformulations that means former training sample, be converted to original training sample as the above formula form, as the training sample of support vector machine:

$S=\{(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_1\right),y_1),(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_2\right),y_2),...,(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_N\right),y_N),\}---\left(10\right)$

Y wherein ₁..., y _nbe the target output of training sample, get S as new input training sample set, so original problem can be converted into following support vector machine primal-dual optimization problem:

$R(\mathrm{\&omega;},b)=\mathrm{\&gamma;}\frac{1}{N}{\mathrm{\&Sigma;}}_{p=1}^N{L}_{\mathrm{\&epsiv;}}(y_p,f\left(X_p\right))+\frac{1}{2}{\mathrm{\&omega;}}^T\mathrm{\&omega;}---\left(11\right)$

Y _pinput training sample X _ptarget output, f (X _p) be corresponding to X _pmodel output, L _ε(y _p, f (X _p)) be input training sample X _pcorresponding target output y _pwith model output f (X _p) once insensitive function when the error margin of optimization problem is ε.γ is the penalty factor of support vector machine, and R (ω, b) is the objective function of optimization problem, and N is number of training, L _ε(y _p, f (X _p)) expression formula is as follows:

Wherein ε is the error margin of optimization problem, next uses support vector machine to try to achieve the optimum derivation linear dimensions of fuzzy rule of fuzzy neural network and the forecast output of primal-dual optimization problem:

$a_{\mathrm{ij}}=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}}=\underset{k\&Element;\mathrm{SV}}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}},i=1,...,R;j=0,...,n---\left(13\right)$

${\hat{y}}_p=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k)<\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X\right),\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_k\right)>+b---\left(14\right)$

Wherein

respectively y _p-f (X _p) be greater than 0 and be less than 0 o'clock corresponding Lagrange multiplier,

p the COD predicted value and the performance variable value that makes the COD emission compliance that training sample is corresponding.

Adaptive structure is optimized module, due to during the structural parameters in fuzzy neural network determine, is mainly to determine by artificial experience, once and definite, whole model structure can not adaptive optimization.This module increases threshold value μ by setting fuzzy rule _th-add, fuzzy rule importance reduces threshold value μ _th-d, fuzzy rule deletes threshold value μ _th-del, the structure to fuzzy neural network in the processing procedure to training sample is carried out the self-adaptation adjustment.In formula (5), fuzzy rule i is for p training sample X _p=[X _p1..., X _pn] fitness be μ ⁽ⁱ⁾(X _p), and in fuzzy rule, the fuzzy rule item of fitness value maximum is:

$I=\arg \underset{1\&le;i\&le;R}{\max }{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)---\left(15\right)$

Wherein

the item No. that means the fuzzy rule item of fitness value maximum,

If μ ( ⁱ)<μ _th-add, fuzzy rule fitness maximal value is less than the fuzzy rule increase threshold value μ of setting _th-add, increase a new regulation.Center and the width of Gauss's member function of the fuzzy rule newly increased are:

$m_j^{\mathrm{new}}=X_{\mathrm{pj}},j=1,...,n---\left(16\right)$

${\mathrm{\&sigma;}}_j^{\mathrm{new}}=\mathrm{\&beta;}\&times;\frac{{\left|\right|X_{\mathrm{pj}}-m_{\mathrm{Ij}}\left|\right|}^2}{{\mathrm{\&sigma;}}_{\mathrm{Ij}}^2},j=1,...,n---\left(17\right)$

Wherein

with

for center and the width of Gauss's member function of new fuzzy rule, constant beta>0 mean new fuzzy rule and the degree of overlapping between fuzzy rule I, generally the β value gets 1.2.In order to prevent that the number of fuzzy rules purpose from constantly increasing, the deletion that adopts a kind of adaptive approach to decide fuzzy rule whether: if i bar fuzzy rule is for the adaptive value μ of p training sample ⁽ⁱ⁾(X _p) be less than fuzzy rule importance and reduce threshold value μ _th-d, its fuzzy rule importance just starts to reduce, otherwise increases, here the importance D of i bar fuzzy rule _imean; If the D of i bar fuzzy rule _ivalue is decreased to fuzzy rule and deletes threshold value μ in to the training sample training process _th-del, leave out i bar fuzzy rule.

The importance values D of each fuzzy rule _i, i=1 ..., the initial value value of R all is set to 1, its with the input training sample change procedure as the formula (18):

D wherein _ithe importance that means i bar fuzzy rule, constant τ value has determined the speed that fuzzy rule importance changes, and gets 1, μ here ⁽ⁱ⁾(X _p) mean the adaptive value of i bar fuzzy rule for p training sample, μ _th-dmean that fuzzy rule importance reduces threshold value.

Work as D _imeet D _i<μ _th-delthe time, μ here _th-delget 0.005, leave out i bar fuzzy rule.

Described host computer also comprises: the discrimination model update module, for the sampling time interval by setting, collection site intelligent instrument signal, the actual measurement chemical oxygen consumption (COC) function predicted value obtained is compared, if relative error be greater than 10% or actual measurement COD data not up to standard, the new data up to standard of producing in the DCS database when normal is added to training sample data, Renewal model.

Display module as a result, for by the COD predicted value with make the performance variable value of COD emission compliance pass to the DCS system, show at the control station of DCS, and be delivered to operator station by DCS system and fieldbus and shown; Simultaneously, the DCS system, using the resulting performance variable value that makes the COD emission compliance as new performance variable setting value, automatically performs the operation of COD emission compliance.

Signal acquisition module, for the time interval of the each sampling according to setting, image data from database.

Described key variables comprise the waste liquid flow that enters incinerator, enter the air mass flow of incinerator and enter the fuel flow rate of incinerator; Described performance variable comprises the air mass flow that enters incinerator and the fuel flow rate that enters incinerator.

2. the control method realized by adaptive pesticide waste liquid incinerator hazardous emission as claimed in claim 1 control system up to standard, it is characterized in that: described method specific implementation step is as follows:

1), to pesticide waste liquid incinerator chemical oxygen demand (COD) discharge process object, according to industrial analysis and Operations Analyst, determine key variables used, when from the DCS database, collection production is normal, the data of described variable, as the input matrix of training sample TX, gather corresponding COD and make the performance variable data of COD emission compliance as output matrix Y;

2), for carrying out pre-service from the model training sample of DCS database input, the average that makes training sample is 0, variance is 1, the following formula process of this processings employing completes:

Computation of mean values: $\stackrel{\&OverBar;}{\mathrm{TX}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{TX}}_i---\left(1\right)$

Calculate variance: ${\mathrm{\&sigma;}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{TX}}_i-\stackrel{\&OverBar;}{\mathrm{TX}})---\left(2\right)$

Standardization: $X=\frac{\mathrm{TX}-\stackrel{\&OverBar;}{\mathrm{TX}}}{{\mathrm{\&sigma;}}_x}---\left(3\right)$

Wherein, TX _ibe i training sample,, be the data of the production that gathers from the DCS database key variables, chemical oxygen consumption (COC) (COD) when normal and the performance variable while making accordingly the COD emission compliance, N is number of training, for the average of training sample, X is the training sample after standardization.σ _xthe standard deviation that means training sample, σ ² _xthe variance that means training sample.

3), to pass the input variable come from data preprocessing module, carry out fuzzy reasoning and set up fuzzy rule.Carry out fuzzy classification to from data preprocessing module, passing the pretreated training sample X of process come, obtain center and the width of each fuzzy clustering in fuzzy rule base.If the training sample X after p standardization _p=[X _p1..., X _pn], wherein n is the number of input variable.

If fuzzy neural network has R fuzzy rule, in order to try to achieve each fuzzy rule for training sample X _peach input variable X _pj, j=1 ..., n, following obfuscation equation will be obtained its degree of membership to i fuzzy rule:

$M_{\mathrm{ij}}=\exp \{-\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(4\right)$

M wherein _ijand σ _ijmean respectively center and the width of j Gauss's member function of i fuzzy rule, tried to achieve by fuzzy clustering.

If training sample X _pfitness to fuzzy rule i is μ ⁽ⁱ⁾(X _p), μ ⁽ⁱ⁾(X _p) large I by following formula, determined:

${\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)=\underset{j=1}{\overset{n}{\mathrm{\&Pi;}}}{M}_{\mathrm{ij}}\left(X_p\right)=\exp \{-\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}\frac{{(X_{\mathrm{pj}}-m_{\mathrm{ij}})}^2}{{\mathrm{\&sigma;}}_{\mathrm{ij}}^2}\}---\left(5\right)$

After trying to achieve the input training sample fitness regular for each, fuzzy neural network is exported and is derived to obtain last analytic solution fuzzy rule.In structure of fuzzy neural network commonly used, the process that each fuzzy rule is derived can be expressed as: at first try to achieve the linear sum of products of all input variables in training sample, then use this linear sum of products and regular relevance grade μ ⁽ⁱ⁾(X _p) multiply each other, obtain the output of every final fuzzy rule.The derivation output of fuzzy rule i can be expressed as follows:

$f^{\left(i\right)}={\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})---\left(6\right)$

${\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b---\left(7\right)$

In formula, f ⁽ⁱ⁾be the output of i bar fuzzy rule,

the prediction output of fuzzy neural network model to p training sample, a _ij, j=1 ..., n is the linear coefficient of j variable in i bar fuzzy rule, a _i0be the constant term of the linear sum of products of input variable in i bar fuzzy rule, b is the output offset amount.

4), in formula (7), the definite of parameter in the linear sum of products of input variable is a subject matter of using during fuzzy neural network is used, here we adopt original fuzzy rule derivation output form are converted to the support vector machine optimization problem, re-use support vector machine and carry out linear optimization, transfer process is as follows:

$\begin{array}{c}{\hat{y}}_p=\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}{f}^{\left(i\right)}+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}[{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;(\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;X_{\mathrm{pj}}+a_{i0})]+b\\ =\underset{i=1}{\overset{R}{\mathrm{\&Sigma;}}}\underset{j=0}{\overset{n}{\mathrm{\&Sigma;}}}{a}_{\mathrm{ij}}\&times;{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)\&times;X_{\mathrm{pj}}+b\end{array}---\left(8\right)$

X wherein _p0for constant term and be constantly equal to 1.Order

$\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_p\right)=[{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(1\right)}\&times;X_{\mathrm{pn}},......,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{p0},...,{\mathrm{\&mu;}}^{\left(R\right)}\&times;X_{\mathrm{pn}}]---\left(9\right)$

Wherein,

the reformulations that means former training sample, be converted to original training sample as the above formula form, as the training sample of support vector machine:

$S=\{(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_1\right),y_1),(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_2\right),y_2),...,(\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_N\right),y_N),\}---\left(10\right)$

Y wherein ₁..., y _nbe the target output of training sample, get S as new input training sample set, so original problem can be converted into following support vector machine primal-dual optimization problem:

$R(\mathrm{\&omega;},b)=\mathrm{\&gamma;}\frac{1}{N}{\mathrm{\&Sigma;}}_{p=1}^N{L}_{\mathrm{\&epsiv;}}(y_p,f\left(X_p\right))+\frac{1}{2}{\mathrm{\&omega;}}^T\mathrm{\&omega;}---\left(11\right)$

Y _pinput training sample X _ptarget output, f (X _p) be corresponding to X _pmodel output, L _ε(y _p, f (X _p)) be input training sample X _pcorresponding target output y _pwith model output f (X _p) once insensitive function when the error margin of optimization problem is ε.γ is the penalty factor of support vector machine, and R (ω, b) is the objective function of optimization problem, and N is number of training, L _ε(y _p, f (X _p)) expression formula is as follows:

Wherein ε is the error margin of optimization problem, next uses support vector machine to try to achieve the optimum derivation linear dimensions of fuzzy rule of fuzzy neural network and the forecast output of primal-dual optimization problem:

$a_{\mathrm{ij}}=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}}=\underset{k\&Element;\mathrm{SV}}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k){\mathrm{\&mu;}}^{\left(i\right)}{X}_{\mathrm{kj}},i=1,...,R;j=0,...,n---\left(13\right)$

${\hat{y}}_p=\underset{k=1}{\overset{N}{\mathrm{\&Sigma;}}}({\mathrm{\&alpha;}}_k^{*}-{\mathrm{\&alpha;}}_k)<\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X\right),\stackrel{\&RightArrow;}{\mathrm{\&phi;}}\left(X_k\right)>+b---\left(14\right)$

Wherein

respectively y _p-f (X _p) be greater than 0 and be less than 0 o'clock corresponding Lagrange multiplier,

p the COD predicted value and the performance variable value that makes the COD emission compliance that training sample is corresponding.

5), set fuzzy rule and increase threshold value μ _th-add, fuzzy rule importance reduces threshold value μ _th-d, fuzzy rule deletes threshold value μ _th-del, the structure to fuzzy neural network in the processing procedure to training sample is carried out the self-adaptation adjustment.In formula (5), fuzzy rule i is for p training sample X _p=[x ₁..., x _n] fitness be μ ⁽ⁱ⁾(X _p), and in fuzzy rule, the fuzzy rule item of fitness value maximum is:

$I=\arg \underset{1\&le;i\&le;R}{\max }{\mathrm{\&mu;}}^{\left(i\right)}\left(X_p\right)---\left(15\right)$

Wherein

the item No. that means the fuzzy rule item of fitness value maximum,

If μ ^(I)<μ _th-add, fuzzy rule fitness maximal value is less than the fuzzy rule increase threshold value μ of setting _th-add, increase a new regulation.Center and the width of Gauss's member function of the fuzzy rule newly increased are:

$m_j^{\mathrm{new}}=X_{\mathrm{pj}},j=1,...,n---\left(16\right)$

${\mathrm{\&sigma;}}_j^{\mathrm{new}}=\mathrm{\&beta;}\&times;\frac{{\left|\right|X_{\mathrm{pj}}-m_{\mathrm{Ij}}\left|\right|}^2}{{\mathrm{\&sigma;}}_{\mathrm{Ij}}^2},j=1,...,n---\left(17\right)$

Wherein with

for center and the width of Gauss's member function of new fuzzy rule, constant beta>0 mean new fuzzy rule and the degree of overlapping between fuzzy rule I, generally the β value gets 1.2.

In order to prevent that the number of fuzzy rules purpose from constantly increasing, the deletion that adopts a kind of adaptive approach to decide fuzzy rule whether: if i bar fuzzy rule is for the adaptive value μ of p training sample ⁽ⁱ⁾(X _p) be less than fuzzy rule importance and reduce threshold value μ _th-d, its fuzzy rule importance just starts to reduce, otherwise increases, here the importance D of i bar fuzzy rule _imean; If the D of i bar fuzzy rule _ivalue is decreased to fuzzy rule and deletes threshold value μ in to the training sample training process _th-del, leave out i bar fuzzy rule.

The importance values D of each fuzzy rule _i, i=1 ..., the initial value value of R all is set to 1, its with the input training sample change procedure as the formula (18):

D wherein _ithe importance that means i bar fuzzy rule, constant τ value has determined the speed that fuzzy rule importance changes, and gets 1, μ here ⁽ⁱ⁾(X _p) mean the adaptive value of i bar fuzzy rule for p training sample, μ _th-dmean that fuzzy rule importance reduces threshold value.

Work as D _imeet D _i<μ _th-delthe time, μ here _th-delget 0.005, leave out i bar fuzzy rule.

6), by the sampling time interval of setting described method also comprises:, collection site intelligent instrument signal, the actual measurement chemical oxygen demand (COD) discharge value function predicted value obtained is compared, if relative error be greater than 10% or actual measurement COD data not up to standard, the new data up to standard of producing in the DCS database when normal is added to training sample data, Renewal model.

7), the COD predicted value obtained in described step 4) and the performance variable value that makes the COD emission compliance, result is passed to the DCS system, show at the control station of DCS, and be delivered to operator station by DCS system and fieldbus and shown; Simultaneously, the DCS system, using the resulting performance variable value that makes the COD emission compliance as new performance variable setting value, automatically performs the operation of COD emission compliance.

Described key variables comprise the waste liquid flow that enters incinerator, enter the air mass flow of incinerator and enter the fuel flow rate of incinerator; Described performance variable comprises the air mass flow that enters incinerator and the fuel flow rate that enters incinerator.

Images