CN103488086B - The pesticide waste liquid incinerator furnace temperature optimization system of optimum FUZZY NETWORK and method - Google Patents
The pesticide waste liquid incinerator furnace temperature optimization system of optimum FUZZY NETWORK and method Download PDFInfo
- Publication number
- CN103488086B CN103488086B CN201310436863.9A CN201310436863A CN103488086B CN 103488086 B CN103488086 B CN 103488086B CN 201310436863 A CN201310436863 A CN 201310436863A CN 103488086 B CN103488086 B CN 103488086B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- munderover
- msup
- math
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000007788 liquid Substances 0.000 title claims abstract description 23
- 239000010914 pesticide waste Substances 0.000 title claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 170
- 238000012706 support-vector machine Methods 0.000 claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000004519 manufacturing process Methods 0.000 claims description 16
- 230000009977 dual effect Effects 0.000 claims description 13
- 239000000446 fuel Substances 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000009795 derivation Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 239000002699 waste material Substances 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims 2
- 230000017105 transposition Effects 0.000 claims 2
- 230000006870 function Effects 0.000 description 17
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000000575 pesticide Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000460 chlorine Substances 0.000 description 1
- 229910052801 chlorine Inorganic materials 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000010815 organic waste Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000000447 pesticide residue Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a kind of pesticide waste liquid incinerator furnace temperature optimization system of optimum FUZZY NETWORK.The method first carries out obfuscation to input variable, utilizes the fuzzy rule in FUZZY NETWORK to derive subsequently, and last support vector machine is used for the linear dimensions in Optimization of Fuzzy neural network.In the method, standardization module, for carrying out standardization to training sample; FUZZY NETWORK module, for soft sensor modeling; Support vector machine optimizes the linear dimensions that module is used in Optimization of Fuzzy mixed-media network modules mixed-media; Result display module, for optimizing furnace temperature predicted value that module obtains and make the performance variable value of furnace temperature the best pass to DCS system from support vector machine.The present invention realizes furnace temperature and accurately controls, avoids occurring that furnace temperature is too low or too high.
Description
Technical Field
The invention relates to the field of pesticide production waste liquid incineration, in particular to a pesticide waste liquid incinerator temperature optimization system and method based on an optimal fuzzy network.
Background
With the rapid development of the pesticide industry, the environmental pollution problem of the emissions has attracted high attention from governments and corresponding environmental protection departments of various countries. The research and the solution of the standard-reaching discharge control and the harmless minimization treatment of the pesticide organic waste liquid not only become the difficulty and the hot point of scientific research of various countries, but also are the scientific proposition of the national urgent need related to the sustainable development of society.
The incineration method is the most effective and thorough method for treating pesticide residue and waste residue at present and is the most common method for application. The temperature of the incinerator must be kept at a proper temperature in the incineration process, and the excessively low incinerator temperature is not beneficial to the decomposition of toxic and harmful components in the waste; the overhigh furnace temperature not only increases the fuel consumption and the equipment operation cost, but also easily damages the inner wall of the hearth and shortens the service life of the equipment. In addition, excessive temperatures may increase the amount of metal volatilization and nitrogen oxide formation in the waste. Particularly for chlorine-containing wastewater, the corrosion of the inner wall can be reduced by proper furnace temperature. However, factors influencing the furnace temperature in the actual incineration process are complex and changeable, and the phenomenon that the furnace temperature is too low or too high is easy to occur.
Zadeh first proposed the concept of a Fuzzy set in 1965 by american mathematician l. Fuzzy logic then begins to replace the classical logic that persists in that everything can be represented in terms of binary terms in a way that it more closely resembles the question and semantic statement of everyday people. In 1987, Bart Kosko's rate first performed a more systematic study of the combination of fuzzy theory and neural networks. In the following time, the theory and application of the fuzzy network are developed rapidly, and the proposal of various new fuzzy network models and the research of the adaptive learning algorithm not only accelerate the perfection of the fuzzy neural theory, but also are widely applied in practice.
The support vector machine, introduced by Vapnik in 1998, converts the original optimal classification problem into a dual optimization problem by using a structure risk minimization method in statistical theory learning instead of a general empirical structure minimization method, thereby having good popularization capability and being widely applied to pattern recognition, fitting and classification problems. In this scheme, a support vector machine is used to optimize the linear parameters in the fuzzy network model.
Disclosure of Invention
In order to overcome the defects that the furnace temperature of the conventional incinerator is difficult to control and is easy to be too low or too high, the invention provides the pesticide waste liquid incinerator temperature optimization system and method for realizing accurate control of the furnace temperature and avoiding too low or too high furnace temperature.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the pesticide waste liquid incinerator temperature optimization system of the optimal fuzzy network comprises an incinerator, an intelligent instrument, a DCS (distributed control system), a data interface and an upper computer, wherein the DCS comprises a control station and a database; on-spot intelligent instrument and DCS headtotail, the DCS system is connected with the host computer, the host computer include:
the standardization processing module is used for preprocessing the model training samples input from the DCS database, centralizing the training samples, namely subtracting the average value of the samples, and then standardizing the training samples:
calculating an average value: <math>
<mrow>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
calculating the variance: <math>
<mrow>
<msubsup>
<mi>σ</mi>
<mi>x</mi>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
and (3) standardization: <math>
<mrow>
<mi>X</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>TX</mi>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
</mrow>
<msub>
<mi>σ</mi>
<mi>x</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
wherein, TXiThe ith training sample is data of key variables, furnace temperature and operating variables for optimizing the furnace temperature during normal production collected from the DCS database, N is the number of training samples,is the mean of the training samples, and X is the normalized training sample. SigmaxRepresenting the standard deviation, σ, of the training samples2 xRepresenting the variance of the training samples.
And the fuzzy network module is used for carrying out fuzzy reasoning and establishing a fuzzy rule on the input variable transmitted from the data preprocessing module. And carrying out fuzzy classification on the preprocessed training sample X transmitted from the data preprocessing module to obtain the center and the width of each fuzzy cluster in the fuzzy rule base. Let the p-th normalized training sample Xp=[Xp1,…,Xpn]Where n is the number of input variables.
Let the fuzzy network have R fuzzy rules, in order to obtain each fuzzy rule for the normalized training sample XpEach input variable X ofpjJ =1, …, n, whose membership to the i-th fuzzy rule is to be found by the following fuzzy equation:
wherein M isijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijAnd respectively representing the center and the width of the jth Gaussian member function of the ith fuzzy rule, and obtaining the center and the width by fuzzy clustering.
Normalized training sample XpFitness to fuzzy rule i is mu(i)(Xp) Then μ(i)(Xp) Can be determined by the following formula:
Mijrepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijRespectively representing the center and width of the jth gaussian member function of the ith fuzzy rule.
After the fitness of the input training sample to each rule is obtained, the fuzzy network deduces the fuzzy rule output to obtain the final analytic solution. In a common fuzzy network structure, the process of deriving each fuzzy rule can be expressed as follows: firstly, the linear product sum of all input variables in the training sample is obtained, and then the linear product sum is used to match the fitness mu of the rule(i)(Xp) And multiplying to obtain the final output of each fuzzy rule. The derived output of the fuzzy rule i can be expressed as follows:
in the formula (f)(i)For the output of the ith fuzzy rule,is the predicted output of the fuzzy network model on the p-th training sample, aijJ =1, …, n is the linear coefficient of the jth variable in the ith fuzzy rule, ai0Is a constant term of the linear product sum of the input variables in the ith fuzzy rule, and b is an output offset.
In formula (7), the determination of parameters in the input variable linear product sum is a main problem used in the use of a fuzzy network, here, an original fuzzy rule derivation output form is converted into a support vector machine optimization problem, and then a support vector machine is used for linear optimization, wherein the conversion process is as follows:
wherein Xp0Is a constant term and is constant equal to 1. Order to
Wherein,the conversion form of the original training sample is represented, namely, the original training sample is converted into the form of the formula as above, and the form is used as the training sample of the support vector machine:
wherein y is1,…,yNThe target output of the training sample is taken, S is taken as a new input training sample set, and then the original problem can be converted into the following dual optimization problem of the support vector machine:
wherein y ispIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpModel output of, L (yp,f(Xp) Is an input training sample XpCorresponding target output ypAnd the model output f (X)p) The first order insensitive function when the error margin of the optimization problem is. Omega is the normal vector of the hyperplane of the support vector machine, f (X)p) Is corresponding to Xpγ is the penalty factor of the support vector machine, the superscript T represents the transpose of the matrix, R (ω, b) is the objective function of the optimization problem, N is the number of training samples, L is the number of training samples (yp,f(Xp) Expression) as follows:
where is the error margin of the optimization problem, ypIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpThen, a support vector machine is used for obtaining the prediction output of the fuzzy rule optimal derivation linear parameters and the dual optimization problem of the fuzzy network:
wherein alpha isk，(k =1, …, N) is yp-f(Xp) Lagrange multipliers corresponding to greater than 0 and less than 0,i.e. corresponding to the p-th normalized training sample XpAnd an operating variable value for optimizing the furnace temperature.
As a preferred solution: the host computer still include: and the model updating module is used for acquiring field intelligent instrument signals according to a set sampling time interval, comparing the obtained actually-measured furnace temperature with a system forecast value, and adding new data which enables the furnace temperature to be optimal when the furnace temperature is normally produced in the DCS database into the training sample data to update the soft measurement model if the relative error is more than 10% or the furnace temperature exceeds the upper and lower normal production limit ranges.
Further, the host computer still include: the result display module is used for transmitting the obtained furnace temperature forecast value and the operation variable value which enables the furnace temperature to be optimal to the DCS, displaying the values at a control station of the DCS and transmitting the values to a field operation station for displaying through the DCS and a field bus; at the same time, the DCS system automatically executes the furnace temperature optimization operation by using the obtained value of the operation variable that optimizes the furnace temperature as a new operation variable set value.
And the signal acquisition module is used for acquiring data from the database according to the set time interval of each sampling.
Still further, the key variables include the flow of waste liquid into the incinerator, the flow of air into the incinerator, and the flow of fuel into the incinerator; the manipulated variables include air flow into the incinerator and fuel flow into the incinerator.
The method for optimizing the furnace temperature of the pesticide waste liquid incinerator by the system for optimizing the furnace temperature of the pesticide waste liquid incinerator with the optimal fuzzy network comprises the following specific implementation steps of:
1) determining used key variables, collecting data of the variables in normal production from a DCS (distributed control system) database as an input matrix of a training sample TX, and collecting corresponding furnace temperature and operation variable data for optimizing the furnace temperature as an output matrix Y;
2) preprocessing a model training sample input from a DCS database, centralizing the training sample, namely subtracting the average value of the sample, and then normalizing the training sample so that the average value is 0 and the variance is 1. The processing is accomplished using the following mathematical process:
2.1) calculating the mean value: <math>
<mrow>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
2.2) calculating the variance: <math>
<mrow>
<msubsup>
<mi>σ</mi>
<mi>x</mi>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
2.3) standardization: <math>
<mrow>
<mi>X</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>TX</mi>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
</mrow>
<msub>
<mi>σ</mi>
<mi>x</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
wherein, TXiThe ith training sample is data of key variables, furnace temperature and operating variables for optimizing the furnace temperature during normal production collected from the DCS database, N is the number of training samples,is the mean of the training samples, and X is the normalized training sample. SigmaxRepresenting the standard deviation, σ, of the training samples2 xRepresenting the variance of the training samples.
3) And carrying out fuzzy reasoning and establishing a fuzzy rule on the input variable transmitted from the data preprocessing module. And carrying out fuzzy classification on the preprocessed training sample X transmitted from the data preprocessing module to obtain the center and the width of each fuzzy cluster in the fuzzy rule base. Let the p-th normalized training sample Xp=[Xp1,…,Xpn]Where n is the number of input variables.
Let the fuzzy network have R fuzzy rules, in order to obtain each fuzzy rule for the normalized training sample XpEach input variable X ofpjJ =1, …, n, whose membership to the i-th fuzzy rule is to be found by the following fuzzy equation:
wherein M isijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijAnd respectively representing the center and the width of the jth Gaussian member function of the ith fuzzy rule, and obtaining the center and the width by fuzzy clustering.
Normalized training sample XpFitness to fuzzy rule i is mu(i)(Xp) Then μ(i)(Xp) Can be determined by the following formula:
Mijrepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijRespectively representing the center and width of the jth gaussian member function of the ith fuzzy rule.
After the fitness of the input training sample to each rule is obtained, the fuzzy network deduces the fuzzy rule output to obtain the final analytic solution. In a common fuzzy network structure, the process of deriving each fuzzy rule can be expressed as follows: headFirst, the linear product sum of all input variables in the training sample is obtained, and then the linear product sum is used to match the fitness mu of the rule(i)(Xp) And multiplying to obtain the final output of each fuzzy rule. The derived output of the fuzzy rule i can be expressed as follows:
in the formula (f)(i)For the output of the ith fuzzy rule,is the predicted output of the fuzzy network model on the p-th training sample, aijJ =1, …, n is the linear coefficient of the jth variable in the ith fuzzy rule, ai0Is a constant term of the linear product sum of the input variables in the ith fuzzy rule, and b is an output offset.
4) In the formula (7), the determination of the parameters in the linear product sum of the input variables is a main problem used in the use of the fuzzy network, here, the original fuzzy rule derivation output form is converted into the optimization problem of the support vector machine, and then the linear optimization is performed by using the support vector machine, wherein the conversion process is as follows:
wherein Xp0Is a constant term and is constant equal to 1. Order to
Wherein,the conversion form of the original training sample is represented, namely, the original training sample is converted into the form of the formula as above, and the form is used as the training sample of the support vector machine:
wherein y is1,…,yNThe target output of the training sample is taken, S is taken as a new input training sample set, and then the original problem can be converted into the following dual optimization problem of the support vector machine:
wherein y ispIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpModel output of, L (yp,f(Xp) Is an input training sample XpCorresponding target output ypAnd the model output f (X)p) The first order insensitive function when the error margin of the optimization problem is. Omega is the normal vector of the hyperplane of the support vector machine, f (X)p) Is corresponding to Xpγ is the penalty factor of the support vector machine, the superscript T represents the transpose of the matrix, R (ω, b) is the objective function of the optimization problem, N is the number of training samples, L is the number of training samples (yp,f(Xp) Expression) as follows:
where is the error margin of the optimization problem, ypIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpThen, a support vector machine is used for obtaining the prediction output of the fuzzy rule optimal derivation linear parameters and the dual optimization problem of the fuzzy network:
wherein alpha isk，(k =1, …, N) is yp-f(Xp) Lagrange multipliers corresponding to greater than 0 and less than 0,i.e. corresponding to the p-th normalized training sample XpAnd an operating variable value for optimizing the furnace temperature.
As a preferred solution: the method further comprises the following steps: 5) acquiring on-site intelligent instrument signals according to a set sampling time interval, comparing the obtained actually-measured furnace temperature with a system forecast value, and if the relative error is more than 10% or the furnace temperature exceeds the upper and lower production normal limit ranges, adding new data which enables the furnace temperature to be optimal when the furnace temperature is normally produced in the DCS database into training sample data, and updating the soft measurement model.
6) Further, calculating to obtain an optimal operating variable value in the step 4), transmitting the furnace temperature forecast value and the operating variable value which enables the furnace temperature to be optimal to the DCS, displaying the values at a control station of the DCS, and transmitting the values to a field operating station through the DCS and a field bus for displaying; at the same time, the DCS system automatically executes the furnace temperature optimization operation by using the obtained value of the operation variable that optimizes the furnace temperature as a new operation variable set value.
Still further, the key variables include the flow of waste liquid into the incinerator, the flow of air into the incinerator, and the flow of fuel into the incinerator; the manipulated variables include air flow into the incinerator and fuel flow into the incinerator.
The technical conception of the invention is as follows: the invention discloses a pesticide waste liquid incinerator temperature optimization system and method based on an optimal fuzzy network, and an operation variable value enabling the incinerator temperature to be optimal is found.
The invention has the following beneficial effects: 1. establishing an online soft measurement model of a quantitative relation between a system key variable and furnace temperature; 2. the operating conditions that optimize the furnace temperature are quickly found.
Drawings
FIG. 1 is a hardware block diagram of the system proposed by the present invention;
fig. 2 is a functional structure diagram of the upper computer according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The examples are intended to illustrate the invention, but not to limit the invention, and any modifications and variations of the invention within the spirit and scope of the claims are intended to fall within the scope of the invention.
Example 1
Referring to fig. 1 and 2, the system for optimizing the temperature of a pesticide waste liquid incinerator by using an optimal fuzzy network comprises a field intelligent instrument 2 connected with an incinerator object 1, a DCS system and an upper computer 6, wherein the DCS system comprises a data interface 3, a control station 4 and a database 5, the field intelligent instrument 2 is connected with the data interface 3, the data interface is connected with the control station 4, the database 5 and the upper computer 6, and the upper computer 6 comprises:
a normalization processing module 7, configured to pre-process the model training samples input from the DCS database, centralize the training samples, that is, subtract the average value of the samples, and then normalize them:
calculating an average value: <math>
<mrow>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
calculating the variance: <math>
<mrow>
<msubsup>
<mi>σ</mi>
<mi>x</mi>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
and (3) standardization: <math>
<mrow>
<mi>X</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>TX</mi>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
</mrow>
<msub>
<mi>σ</mi>
<mi>x</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
wherein, TXiThe ith training sample is data of key variables, furnace temperature and operating variables for optimizing the furnace temperature during normal production collected from the DCS database, N is the number of training samples,is the mean of the training samples, and X is the normalized training sample. SigmaxRepresenting the standard deviation, σ, of the training samples2 xRepresenting the variance of the training samples.
And the fuzzy network module 8 is used for carrying out fuzzy reasoning and establishing a fuzzy rule on the input variable transmitted from the data preprocessing module. And carrying out fuzzy classification on the preprocessed training sample X transmitted from the data preprocessing module to obtain the center and the width of each fuzzy cluster in the fuzzy rule base. Let the p-th normalized training sample Xp=[Xp1,…,Xpn]Where n is the number of input variables.
Let the fuzzy network have R fuzzy rules, in order to obtain each fuzzy rule for the normalized training sample XpEach input variable X ofpjJ =1, …, n, whose membership to the i-th fuzzy rule is to be found by the following fuzzy equation:
wherein M isijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijThe center and width of the jth Gaussian member function respectively representing the ith fuzzy ruleAnd (5) fuzzy clustering.
Normalized training sample XpFitness to fuzzy rule i is mu(i)(Xp) Then μ(i)(Xp) Can be determined by the following formula:
Mijrepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijRespectively representing the center and width of the jth gaussian member function of the ith fuzzy rule.
After the fitness of the input training sample to each rule is obtained, the fuzzy network deduces the fuzzy rule output to obtain the final analytic solution. In a common fuzzy network structure, the process of deriving each fuzzy rule can be expressed as follows: firstly, the linear product sum of all input variables in the training sample is obtained, and then the linear product sum is used to match the fitness mu of the rule(i)(Xp) And multiplying to obtain the final output of each fuzzy rule. The derived output of the fuzzy rule i can be expressed as follows:
in the formula (f)(i)For the output of the ith fuzzy rule,is the predicted output of the fuzzy network model on the p-th training sample, aijJ =1, …, n is the linear coefficient of the jth variable in the ith fuzzy rule, ai0Is a constant term of the linear product sum of the input variables in the ith fuzzy rule, and b is an output offset.
In formula (7), the determination of the parameters in the input variable linear product sum is a main problem used in the use of the fuzzy network, here, the original fuzzy rule derivation output form is converted into the support vector machine optimization problem, and then the support vector machine is used for linear optimization, and the conversion process is as follows:
wherein Xp0Is a constant term and is constant equal to 1. Order to
Wherein,the conversion form of the original training sample is represented, namely, the original training sample is converted into the form of the formula as above, and the form is used as the training sample of the support vector machine:
wherein y is1,…,yNThe target output of the training sample is taken, S is taken as a new input training sample set, and then the original problem can be converted into the following dual optimization problem of the support vector machine:
wherein y ispIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpModel output of, L (yp,f(Xp) Is an input training sample XpCorresponding target output ypAnd the model output f (X)p) The first order insensitive function when the error margin of the optimization problem is. Omega is the normal vector of the hyperplane of the support vector machine, f (X)p) Is corresponding to Xpγ is the penalty factor of the support vector machine, the superscript T represents the transpose of the matrix, R (ω, b) is the objective function of the optimization problem, N is the number of training samples, L is the number of training samples (yp,f(Xp) Expression) as follows:
where is the error margin of the optimization problem, ypIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpThen, a support vector machine is used for obtaining the prediction output of the fuzzy rule optimal derivation linear parameters and the dual optimization problem of the fuzzy network:
wherein alpha isk，(k =1, …, N) is yp-f(Xp) Lagrange multipliers corresponding to greater than 0 and less than 0,i.e. corresponding to the p-th normalized training sample XpAnd an operating variable value for optimizing the furnace temperature.
The upper computer 6 further comprises: and the signal acquisition module 11 is used for acquiring data from the database according to a set time interval of each sampling.
The upper computer 6 further comprises: and the model updating module 12 is used for acquiring field intelligent instrument signals according to a set sampling time interval, comparing the obtained actually-measured furnace temperature with a system forecast value, and adding new data which enables the furnace temperature to be optimal when the furnace temperature is normally produced in the DCS database into the training sample data to update the soft measurement model if the relative error is more than 10% or the furnace temperature exceeds the upper and lower normal production limit ranges.
The key variables include the flow of waste liquid into the incinerator, the flow of air into the incinerator and the flow of fuel into the incinerator; the manipulated variables include air flow into the incinerator and fuel flow into the incinerator.
The system also comprises a DCS (distributed control system), wherein the DCS is composed of a data interface 3, a control station 4 and a database 5; the intelligent instrument 2, the DCS system and the upper computer 6 are sequentially connected through a field bus; the upper computer 6 further comprises a result display module 10, which is used for transmitting the calculation optimal result to the DCS system, displaying the process state at the control station of the DCS, and transmitting the process state information to the field operation station for displaying through the DCS system and the field bus.
When the waste liquid incineration process is provided with the DCS system, the detection and storage of the real-time dynamic data of the sample are mainly completed on the upper computer by utilizing the real-time and historical databases of the DCS system to obtain the furnace temperature forecast value and the operation variable value for optimizing the furnace temperature.
When the waste liquid incineration process is not provided with the DCS system, the data memory is adopted to replace the data storage function of a real-time and historical database of the DCS system, and the functional system for obtaining the furnace temperature forecast value and the operation variable value for optimizing the furnace temperature is manufactured into an independent complete system-on-chip which comprises an I/O element, a data memory, a program memory, an arithmetic unit and a display module and does not depend on the DCS system, so that the system-on-chip can be independently used regardless of whether the incineration process is provided with the DCS or not, and is more beneficial to popularization and use.
Example 2
Referring to fig. 1 and 2, the method for optimizing the temperature of the pesticide waste liquid incinerator by using the optimal fuzzy network specifically comprises the following implementation steps:
1) determining used key variables, collecting data of the variables in normal production from a DCS (distributed control system) database as an input matrix of a training sample TX, and collecting corresponding furnace temperature and operation variable data for optimizing the furnace temperature as an output matrix Y;
2) preprocessing a model training sample input from a DCS database, centralizing the training sample, namely subtracting the average value of the sample, and then normalizing the training sample so that the average value is 0 and the variance is 1. The processing is accomplished using the following mathematical process:
2.1) calculating the mean value: <math>
<mrow>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
2.2) calculating the variance: <math>
<mrow>
<msubsup>
<mi>σ</mi>
<mi>x</mi>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
<munderover>
<mi>Σ</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
2.3) standardization: <math>
<mrow>
<mi>X</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>TX</mi>
<mo>-</mo>
<mover>
<mi>TX</mi>
<mo>‾</mo>
</mover>
</mrow>
<msub>
<mi>σ</mi>
<mi>x</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
wherein, TXiThe ith training sample is data of key variables, furnace temperature and operation variables for optimizing the furnace temperature during normal production collected from the DCS database, NIn order to train the number of samples,is the mean of the training samples, and X is the normalized training sample. SigmaxRepresenting the standard deviation, σ, of the training samples2 xRepresenting the variance of the training samples.
3) And carrying out fuzzy reasoning and establishing a fuzzy rule on the input variable transmitted from the data preprocessing module. And carrying out fuzzy classification on the preprocessed training sample X transmitted from the data preprocessing module to obtain the center and the width of each fuzzy cluster in the fuzzy rule base. Let the p-th normalized training sample Xp=[Xp1,…,Xpn]Where n is the number of input variables.
Let the fuzzy network have R fuzzy rules, in order to obtain each fuzzy rule for the normalized training sample XpEach input variable X ofpjJ =1, …, n, whose membership to the i-th fuzzy rule is to be found by the following fuzzy equation:
wherein M isijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijAnd respectively representing the center and the width of the jth Gaussian member function of the ith fuzzy rule, and obtaining the center and the width by fuzzy clustering.
Normalized training sample XpFitness to fuzzy rule i is mu(i)(Xp) Then μ(i)(Xp) Can be determined by the following formula:
Mijrepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijIndividual watchThe center and width of the jth gaussian member function of the ith fuzzy rule are shown.
After the fitness of the input training sample to each rule is obtained, the fuzzy network deduces the fuzzy rule output to obtain the final analytic solution. In a common fuzzy network structure, the process of deriving each fuzzy rule can be expressed as follows: firstly, the linear product sum of all input variables in the training sample is obtained, and then the linear product sum is used to match the fitness mu of the rule(i)(Xp) And multiplying to obtain the final output of each fuzzy rule. The derived output of the fuzzy rule i can be expressed as follows:
in the formula (f)(i)For the output of the ith fuzzy rule,is the predicted output of the fuzzy network model on the p-th training sample, aijJ =1, …, n is the linear coefficient of the jth variable in the ith fuzzy rule, ai0Is a constant term of the linear product sum of the input variables in the ith fuzzy rule, and b is an output offset.
4) In the formula (7), the determination of the parameters in the linear product sum of the input variables is a main problem used in the use of the fuzzy network, here, the original fuzzy rule derivation output form is converted into the optimization problem of the support vector machine, and then the linear optimization is performed by using the support vector machine, wherein the conversion process is as follows:
wherein Xp0Is a constant term and is constant equal to 1. Order to
Wherein,the conversion form of the original training sample is represented, namely, the original training sample is converted into the form of the formula as above, and the form is used as the training sample of the support vector machine:
wherein y is1,…,yNThe target output of the training sample is taken, S is taken as a new input training sample set, and then the original problem can be converted into the following dual optimization problem of the support vector machine:
wherein y ispIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpModel output of, L (yp,f(Xp) Is an input training sample XpCorresponding target output ypAnd the model output f (X)p) The first order insensitive function when the error margin of the optimization problem is. Omega is the normal vector of the hyperplane of the support vector machine, f (X)p) Is corresponding to Xpγ is the penalty factor of the support vector machine, the superscript T represents the transpose of the matrix, R (ω, b) is the objective function of the optimization problem, N is the number of training samples, L is the number of training samples (yp,f(Xp) Expression) as follows:
where is the error margin of the optimization problem, ypIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpThen, a support vector machine is used for obtaining the prediction output of the fuzzy rule optimal derivation linear parameters and the dual optimization problem of the fuzzy network:
wherein alpha isk，(k =1, …, N) is yp-f(Xp) Lagrange multipliers corresponding to greater than 0 and less than 0,i.e. corresponding to the p-th normalized training sample XpAnd an operating variable value for optimizing the furnace temperature.
The method further comprises the following steps: 5) acquiring on-site intelligent instrument signals according to a set sampling time interval, comparing the obtained actually-measured furnace temperature with a system forecast value, and if the relative error is more than 10% or the furnace temperature exceeds the upper and lower production normal limit ranges, adding new data which enables the furnace temperature to be optimal when the furnace temperature is normally produced in the DCS database into training sample data, and updating the soft measurement model.
Calculating to obtain an optimal operation variable value in the step 4), transmitting the obtained furnace temperature forecast value and the operation variable value which enables the furnace temperature to be optimal to the DCS, displaying the values at a control station of the DCS, and transmitting the values to a field operation station for displaying through the DCS and a field bus; at the same time, the DCS system automatically executes the furnace temperature optimization operation by using the obtained value of the operation variable that optimizes the furnace temperature as a new operation variable set value.
The key variables include the flow of waste liquid into the incinerator, the flow of air into the incinerator and the flow of fuel into the incinerator; the manipulated variables include air flow into the incinerator and fuel flow into the incinerator.
Claims (2)
1. A pesticide waste liquid incinerator temperature optimization system of an optimal fuzzy network comprises an incinerator, a field intelligent instrument, a DCS (distributed control system), a data interface and an upper computer, wherein the DCS comprises a control station and a database; on-spot intelligent instrument and DCS headtotail, the DCS system is connected with the host computer, its characterized in that: the host computer include:
the standardization processing module is used for preprocessing the model training samples input from the DCS database, centralizing the training samples, namely subtracting the average value of the samples, and then standardizing the training samples:
calculating an average value: <math>
<mrow>
<mover>
<mrow>
<mi>T</mi>
<mi>X</mi>
</mrow>
<mo>‾</mo>
</mover>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mo>Σ</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
calculating the variance: <math>
<mrow>
<msubsup>
<mi>σ</mi>
<mi>x</mi>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
<munderover>
<mo>Σ</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mover>
<mrow>
<mi>T</mi>
<mi>X</mi>
</mrow>
<mo>‾</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
and (3) standardization: <math>
<mrow>
<mi>X</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>T</mi>
<mi>X</mi>
<mo>-</mo>
<mover>
<mrow>
<mi>T</mi>
<mi>X</mi>
</mrow>
<mo>‾</mo>
</mover>
</mrow>
<msub>
<mi>σ</mi>
<mi>x</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
wherein TX is a training sample, TXiThe ith training sample is data of key variables, furnace temperature and operating variables for optimizing the furnace temperature during normal production collected from the DCS database, N is the number of training samples,is the mean value of the training sample, and X is the training sample after standardization; sigmaxRepresenting the standard deviation, σ, of the training samples2 xRepresenting the variance of the training samples;
the fuzzy network module is used for carrying out fuzzy reasoning and establishing a fuzzy rule on the input variable transmitted from the standardized processing module; carrying out fuzzy classification on the preprocessed training sample X transmitted from the standardized processing module to obtain the center and the width of each fuzzy cluster in a fuzzy rule base; let the p-th normalized training sample Xp＝[Xp1,...,Xpn]Where n is the number of input variables;
let the fuzzy neural network have R fuzzy rules, in order to obtain each fuzzy rule for the normalized training sample XpEach input variable X ofpjJ is 1, …, n, and the following blurring equation will find its membership to the ith fuzzy rule:
wherein M isijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijRespectively representing the center and the width of a jth Gaussian member function of the ith fuzzy rule, and obtaining the center and the width by fuzzy clustering;
normalized training sample XpFitness to fuzzy rule i is mu(i)(Xp) Then μ(i)(Xp) Can be determined by the following formula:
in the formula, MijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijRespectively representing the center and the width of a jth Gaussian member function of the ith fuzzy rule;
after the fitness of the input training sample to each rule is obtained, the fuzzy neural network deduces the output of the fuzzy rule to obtain the final analytic solution; in a commonly used fuzzy neural network structure, the process of deriving each fuzzy rule can be expressed as follows: firstly, the linear product sum of all input variables in the training sample is obtained, and then the linear product sum is used to match the fitness mu of the rule(i)(Xp) Multiplying to obtain the final output of each fuzzy rule; the derived output of the fuzzy rule i can be expressed as follows:
in the formula (f)(i)For the output of the ith fuzzy rule,is the predicted output of the fuzzy neural network model to the p-th training sample, aijJ is 1, …, n is the linear coefficient of the jth variable in the ith fuzzy rule, ai0Is the constant term of the input variable linear product sum in the ith fuzzy rule, and b is the output offset;
in formula (7), the determination of parameters in the input variable linear product sum is a main problem used in the use of the fuzzy neural network, here, the original fuzzy rule derivation output form is converted into the support vector machine optimization problem, and then the support vector machine is used for linear optimization, wherein the conversion process is as follows:
wherein Xp0Is a constant term and is constant equal to 1; order to
Wherein,the conversion form of the original training sample is represented, namely, the original training sample is converted into the form of the formula as above, and the form is used as the training sample of the support vector machine:
wherein y is1,…,yNThe target output of the training sample is taken, S is taken as a new input training sample set, and then the original problem can be converted into the following dual optimization problem of the support vector machine:
wherein y ispIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpModel output of, L (yp,f(Xp) Is an input training sample XpCorresponding target output ypAnd the model output f (X)p) A first order insensitive function when the error tolerance of the optimization problem is; omega is the hyperplane normal vector of the support vector machine, gamma is the penalty factor of the support vector machine, superscript T represents the transposition of the matrix, R (omega, b) is the objective function of the optimization problem, N is the number of training samples, L (yp,f(Xp) Expression) as follows:
where is the error margin of the optimization problem, ypIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpThen, a support vector machine is used for obtaining the prediction output of the fuzzy rule optimal derivation linear parameters and the dual optimization problem of the fuzzy neural network:
wherein alpha isk，(k is 1, …, N) is yp-f(Xp) Lagrange multipliers corresponding to greater than 0 and less than 0,i.e. corresponding to the p-th normalized training sample XpThe furnace temperature predicted value and the operation variable value for optimizing the furnace temperature;
the host computer still include:
the model updating module is used for acquiring field intelligent instrument signals according to a set sampling time interval, comparing the obtained actually-measured furnace temperature with a system forecast value, and if the relative error is more than 10% or the furnace temperature exceeds the upper and lower production normal limit ranges, adding new data which enables the furnace temperature to be optimal when the furnace temperature is normally produced in the DCS database into training sample data, and updating the soft measurement model;
the result display module is used for transmitting the obtained furnace temperature forecast value and the operation variable value which enables the furnace temperature to be optimal to the DCS, displaying the values at a control station of the DCS and transmitting the values to a field operation station for displaying through the DCS and a field bus; meanwhile, the DCS system takes the obtained operating variable value which enables the furnace temperature to be optimal as a new operating variable set value, and automatically executes furnace temperature optimization operation;
the signal acquisition module is used for acquiring data from the database according to the set time interval of each sampling;
the key variables include the flow of waste liquid into the incinerator, the flow of air into the incinerator and the flow of fuel into the incinerator; the manipulated variables include air flow into the incinerator and fuel flow into the incinerator.
2. A pesticide waste liquid incinerator temperature optimization method of an optimal fuzzy network is characterized by comprising the following steps: the furnace temperature optimization method comprises the following specific implementation steps:
1) determining used key variables, collecting data of the variables in normal production from a DCS (distributed control system) database as an input matrix of a training sample TX, and collecting corresponding furnace temperature and operation variable data for optimizing the furnace temperature as an output matrix Y;
2) preprocessing a model training sample input from a DCS database, centralizing the training sample, namely subtracting the average value of the sample, and then standardizing the training sample to ensure that the average value is 0 and the variance is 1; the processing is accomplished using the following mathematical process:
2.1) calculating the mean value: <math>
<mrow>
<mover>
<mrow>
<mi>T</mi>
<mi>X</mi>
</mrow>
<mo>‾</mo>
</mover>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>N</mi>
</mfrac>
<munderover>
<mo>Σ</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
2.2) calculating the variance: <math>
<mrow>
<msubsup>
<mi>σ</mi>
<mi>x</mi>
<mn>2</mn>
</msubsup>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
<munderover>
<mo>Σ</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mrow>
<mo>(</mo>
<msub>
<mi>TX</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mover>
<mrow>
<mi>T</mi>
<mi>X</mi>
</mrow>
<mo>‾</mo>
</mover>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
2.3) standardization: <math>
<mrow>
<mi>X</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>T</mi>
<mi>X</mi>
<mo>-</mo>
<mover>
<mrow>
<mi>T</mi>
<mi>X</mi>
</mrow>
<mo>‾</mo>
</mover>
</mrow>
<msub>
<mi>σ</mi>
<mi>x</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
</math>
wherein TX is a training sample, TXiThe ith training sample is data of key variables, furnace temperature and operating variables for optimizing the furnace temperature during normal production collected from the DCS database, N is the number of training samples,is the mean value of the training sample, and X is the training sample after standardization; sigmaxRepresenting the standard deviation, σ, of the training samples2 xRepresenting the variance of the training samples;
3) carrying out fuzzy reasoning and establishing a fuzzy rule on the input variable transmitted from the standardized processing module; carrying out fuzzy classification on the preprocessed training sample X transmitted from the standardized processing module to obtain the center and the width of each fuzzy cluster in a fuzzy rule base; let the p-th normalized training sample Xp＝[Xp1,...,Xpn]Where n is the number of input variables;
let the fuzzy neural network have R fuzzy rules, in order to obtain each fuzzy rule for the normalized training sample XpEach input variable X ofpjJ is 1, …, n, and the following blurring equation will find its membership to the ith fuzzy rule:
whereinMijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijRespectively representing the center and the width of a jth Gaussian member function of the ith fuzzy rule, and obtaining the center and the width by fuzzy clustering;
normalized training sample XpFitness to fuzzy rule i is mu(i)(Xp) Then μ(i)(Xp) Can be determined by the following formula:
in the formula, MijRepresenting an input variable XpjDegree of membership, m, to the ith fuzzy ruleijAnd σijRespectively representing the center and the width of a jth Gaussian member function of the ith fuzzy rule;
after the fitness of the input training sample to each rule is obtained, the fuzzy neural network deduces the output of the fuzzy rule to obtain the final analytic solution; in a commonly used fuzzy neural network structure, the process of deriving each fuzzy rule can be expressed as follows: firstly, the linear product sum of all input variables in the training sample is obtained, and then the linear product sum is used to match the fitness mu of the rule(i)(Xp) Multiplying to obtain the final output of each fuzzy rule; the derived output of the fuzzy rule i can be expressed as follows:
in the formula (f)(i)Obfuscating rules for the ith stripeIs then outputted from the output of (a),is the predicted output of the fuzzy neural network model to the p-th training sample, aijJ is 1, …, n is the linear coefficient of the jth variable in the ith fuzzy rule, ai0Is the constant term of the input variable linear product sum in the ith fuzzy rule, and b is the output offset;
4) in the formula (7), the determination of the parameters in the linear product sum of the input variables is a main problem used in the use of the fuzzy neural network, here, the original fuzzy rule derivation output form is converted into the optimization problem of the support vector machine, and then the linear optimization is performed by using the support vector machine, wherein the conversion process is as follows:
wherein Xp0Is a constant term and is constant equal to 1; order to
Wherein,the conversion form of the original training sample is represented, namely, the original training sample is converted into the form of the formula as above, and the form is used as the training sample of the support vector machine:
wherein y is1,…,yNThe target output of the training sample is taken, S is taken as a new input training sample set, and then the original problem can be converted into the following dual optimization problem of the support vector machine:
wherein y ispIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpModel output of, L (yp,f(Xp) Is an input training sample XpCorresponding target output ypAnd the model output f (X)p) First order insensitivity function when the error margin of the optimization problem isCounting; omega is the hyperplane normal vector of the support vector machine, gamma is the penalty factor of the support vector machine, superscript T represents the transposition of the matrix, R (omega, b) is the objective function of the optimization problem, N is the number of training samples, L (yp,f(Xp) Expression) as follows:
● where is the error margin y of the optimization problempIs inputting a training sample XpTarget output of f (X)p) Is corresponding to XpThen, a support vector machine is used for obtaining the prediction output of the fuzzy rule optimal derivation linear parameters and the dual optimization problem of the fuzzy neural network:
wherein alpha isk，(k is 1, …, N) is yp-f(Xp) Lagrange multipliers corresponding to greater than 0 and less than 0,i.e. corresponding to the p-th normalized training sample XpThe furnace temperature predicted value and the operation variable value for optimizing the furnace temperature;
the method further comprises the following steps:
5) acquiring field intelligent instrument signals according to a set sampling time interval, comparing the obtained actually-measured furnace temperature with a system forecast value, and if the relative error is more than 10% or the furnace temperature exceeds the upper and lower production normal limit ranges, adding new data which enables the furnace temperature to be optimal when the furnace temperature is normally produced in a DCS database into training sample data, and updating a soft measurement model;
6) calculating to obtain an optimal operating variable value in the step 4), transmitting the furnace temperature forecast value and the operating variable value which enables the furnace temperature to be optimal to the DCS, displaying the values at a control station of the DCS, and transmitting the values to a field operating station through the DCS and a field bus for displaying; meanwhile, the DCS system takes the obtained operating variable value which enables the furnace temperature to be optimal as a new operating variable set value, and automatically executes furnace temperature optimization operation;
the key variables include the flow of waste liquid into the incinerator, the flow of air into the incinerator and the flow of fuel into the incinerator; the manipulated variables include air flow into the incinerator and fuel flow into the incinerator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310436863.9A CN103488086B (en) | 2013-09-22 | 2013-09-22 | The pesticide waste liquid incinerator furnace temperature optimization system of optimum FUZZY NETWORK and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310436863.9A CN103488086B (en) | 2013-09-22 | 2013-09-22 | The pesticide waste liquid incinerator furnace temperature optimization system of optimum FUZZY NETWORK and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103488086A CN103488086A (en) | 2014-01-01 |
| CN103488086B true CN103488086B (en) | 2015-09-16 |
Family
ID=49828405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310436863.9A Expired - Fee Related CN103488086B (en) | 2013-09-22 | 2013-09-22 | The pesticide waste liquid incinerator furnace temperature optimization system of optimum FUZZY NETWORK and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103488086B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168067B (en) * | 2017-06-26 | 2020-03-13 | 北京工业大学 | Fuzzy control method for temperature of garbage incinerator by adopting case reasoning and extraction rules |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07126663A (en) * | 1993-10-25 | 1995-05-16 | Kawasaki Heavy Ind Ltd | Slag flow-down monitoring in coal partial combustion furnace and monitoring device therefor |
| WO2008031177A1 (en) * | 2006-09-11 | 2008-03-20 | Gerdau Açominas S/A | Process using artificial neural network for predictive control in sinter machine |
| CN101751051A (en) * | 2008-12-05 | 2010-06-23 | 中国科学院沈阳自动化研究所 | Cement decomposing furnace temperature control method based on constraint smith GPC |
| CN101763085A (en) * | 2009-12-29 | 2010-06-30 | 浙江大学 | System and method for optimizing temperature of pesticide production waste liquid incinerator |
| CN101763084A (en) * | 2009-12-29 | 2010-06-30 | 浙江大学 | System and method for minimizing chemical oxygen demand (COD) discharge of pesticide production waste liquid incinerator |
-
2013
- 2013-09-22 CN CN201310436863.9A patent/CN103488086B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07126663A (en) * | 1993-10-25 | 1995-05-16 | Kawasaki Heavy Ind Ltd | Slag flow-down monitoring in coal partial combustion furnace and monitoring device therefor |
| WO2008031177A1 (en) * | 2006-09-11 | 2008-03-20 | Gerdau Açominas S/A | Process using artificial neural network for predictive control in sinter machine |
| CN101751051A (en) * | 2008-12-05 | 2010-06-23 | 中国科学院沈阳自动化研究所 | Cement decomposing furnace temperature control method based on constraint smith GPC |
| CN101763085A (en) * | 2009-12-29 | 2010-06-30 | 浙江大学 | System and method for optimizing temperature of pesticide production waste liquid incinerator |
| CN101763084A (en) * | 2009-12-29 | 2010-06-30 | 浙江大学 | System and method for minimizing chemical oxygen demand (COD) discharge of pesticide production waste liquid incinerator |
Non-Patent Citations (1)
| Title |
|---|
| 有机废液焚烧炉控制***设计;潘华丰,刘兴高;《控制工程》;20090720;第16卷(第S2期);第53-56页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103488086A (en) | 2014-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Young | Handbook of regression methods | |
| Liu et al. | A mixture of variational canonical correlation analysis for nonlinear and quality-relevant process monitoring | |
| CN103472865B (en) | The pesticide waste liquid incinerator furnace temperature optimization system of intelligence least square and method | |
| Huang et al. | Forecasting energy fluctuation model by wavelet decomposition and stochastic recurrent wavelet neural network | |
| Sadiq et al. | Probability density functions based weights for ordered weighted averaging (OWA) operators: An example of water quality indices | |
| CN101763085B (en) | System and method for optimizing temperature of pesticide production waste liquid incinerator | |
| Abbasi et al. | Monthly and seasonal modeling of municipal waste generation using radial basis function neural network | |
| Yan et al. | DSTED: A denoising spatial–temporal encoder–decoder framework for multistep prediction of burn-through point in sintering process | |
| CN106199174A (en) | Extruder energy consumption predicting abnormality method based on transfer learning | |
| Wu et al. | Online detection of steady-state operation using a multiple-change-point model and exact Bayesian inference | |
| Lv et al. | Non-iterative T–S fuzzy modeling with random hidden-layer structure for BFG pipeline pressure prediction | |
| Shi et al. | A CNN-LSTM based deep learning model with high accuracy and robustness for carbon price forecasting: A case of Shenzhen's carbon market in China | |
| Kosana et al. | Hybrid wind speed prediction framework using data pre-processing strategy based autoencoder network | |
| CN103472721B (en) | The pesticide waste liquid incinerator furnace temperature optimization system of self-adaptation machine learning and method | |
| Fisher et al. | Data-driven modelling for resource recovery: Data volume, variability, and visualisation for an industrial bioprocess | |
| Zhenjie et al. | A novel nonlinear causal inference approach using vector‐based belief rule base | |
| CN103472867B (en) | The optimizing temperature of pesticide production waste liquid incinerator system and method for support vector machine | |
| Zhang et al. | A behavior prediction method for complex system based on belief rule base with structural adaptive | |
| CN103488086B (en) | The pesticide waste liquid incinerator furnace temperature optimization system of optimum FUZZY NETWORK and method | |
| CN103488089B (en) | Adaptive pesticide waste liquid incinerator hazardous emission controls up to par system and method | |
| Jiang et al. | Rule-based expert system to assess caving output ratio in top coal caving | |
| CN103675010A (en) | Supporting-vector-machine-based industrial melt index soft measuring meter and method | |
| CN103675005A (en) | Soft industrial melt index measurement instrument and method for optimal fuzzy network | |
| Lu et al. | Petroleum demand forecasting for Taiwan using modified fuzzy‐grey algorithms | |
| CN103488208B (en) | The optimizing temperature of pesticide production waste liquid incinerator system and method for least square |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150916 Termination date: 20180922 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |