CN103674778B - The industrial melt index soft measurement instrument of RBF particle group optimizing and method - Google Patents

Abstract

The invention discloses a kind of industrial melt index soft measurement instrument and method of RBF particle group optimizing.This soft side metering method adopts through the training set of pretreated training sample as RBF neural, carries out Fuzzy processing subsequently and use particle cluster algorithm to be optimized to the Output rusults of network.In the present invention, field intelligent instrument, control station for measuring easily survey variable are connected with DCS database, hard measurement value display instrument comprises the industrial melt index soft measurement model of RBF particle group optimizing, DCS database is connected with the input end of soft-sensing model, and the output terminal of the industrial melt index soft measurement model of described RBF particle group optimizing is connected with melt index flexible measured value display instrument; The present invention has on-line optimization, input automatically updating data, feature that noise resisting ability is strong.

Description

The industrial melt index soft measurement instrument of RBF particle group optimizing and method

Technical field

The present invention designs soft measuring instrument and method, and the industrial melt index soft particularly relating to a kind of RBF particle group optimizing measures soft measuring instrument and method.

Background technology

Polypropylene is a kind of hemicrystalline thermoplastics by propylene polymerization, and have higher resistance to impact, engineering properties is tough, and anti-multiple organic solvent and acid and alkali corrosion, being widely used in industry member, is one of usual modal macromolecular material.Melting index (MI) determines one of important quality index of the final products trade mark during polypropylene is produced, and which determines the different purposes of product.Melting index accurate, measure timely, to production and scientific research, have very important effect and directive significance.But the on-line analysis of melting index is measured and is still difficult to accomplish at present, the in-line analyzer lacking melting index is a subject matter of restriction polypropylene product quality.MI can only pass through hand sampling, off-line assay obtains, and general every 2-4 hour analyzes once, and time lag is large, is difficult to meet the requirement of producing and controlling in real time.

Artificial neural network in recent years, especially RBF neural, achieve good effect in system optimization.Neural network has very strong self-adaptation, self-organization, the ability of self study and the ability of large-scale parallel computing.But in actual applications, neural network also exposes some self intrinsic defects: the initialization of weights is random, is easily absorbed in local minimum; In learning process, the interstitial content of hidden layer and the selection of other parameters can only rule of thumb be selected with experiment; Convergence time is long, poor robustness etc.Secondly, the DCS data that industry spot collects also because noise, manual operation error etc. are with certain uncertain error, so use the general Generalization Ability of forecasting model of the artificial neural network that determinacy is strong or not.

Nineteen sixty-five U.S. mathematician L.Zadeh first proposed the concept of fuzzy set.Subsequently fuzzy logic with its problem closer to daily people and the meaning of one's words statement mode, start the classical logic replacing adhering to that all things can represent with binary item.Fuzzy logic so far successful Application among multiple fields of industry, the such as field such as household electrical appliances, Industry Control.2003, Demirci proposed the concept of fuzzifying equation, by using fuzzy membership matrix and the input matrix new with its distortion structure one, then in local equation, showed that analytic value is as last output using the gravity model appoach in Anti-fuzzy method.For the hard measurement of melting index in propylene polymerization production process, consider the noise effect in industrial processes and operate miss, the fuzzy performance of fuzzy logic can be used to reduce error to the impact of whole forecast precision.

Particle cluster algorithm, i.e. Particle Swarm Optimization, being a kind of a kind of biological intelligence optimizing algorithm seeking global optimum by imitating birds flight data dispose put forward by Kennedy and Eberhart professor, being called for short PSO.This algorithm is influenced each other by interparticle in colony, decreases the risk that searching algorithm is absorbed in locally optimal solution, has good global search performance.Particle cluster algorithm is used to the best parameter group searching for RBF neural fuzzifying equation, to reach the object of Optimized model.Summary of the invention

In order to overcome the deficiency that measuring accuracy is not high, low to noise sensitivity, parameter choose difficulty is large of existing propylene polymerization production process, the invention provides a kind of on-line measurement, computing velocity is fast, model upgrades automatically, the industrial melting index propylene polymerization production process melting index soft measuring instrument of RBF particle group optimizing that noise resisting ability is strong and method.

A kind of industrial melt index soft of RBF particle group optimizing measures soft measuring instrument, comprise propylene polymerization production process, for measuring the field intelligent instrument easily surveying variable, for measuring the control station of performance variable, the DCS database of store data and melt index flexible measured value display instrument, described field intelligent instrument, control station is connected with propylene polymerization production process, described field intelligent instrument, control station is connected with DCS database, described soft measuring instrument also comprises the industrial melt index soft measurement model of RBF particle group optimizing, described DCS database is connected with the input end of the industrial melt index soft measurement model of described RBF particle group optimizing, the output terminal of the industrial melt index soft measurement model of described RBF particle group optimizing is connected with melt index flexible measured value display instrument, the industrial melt index soft measurement model of described RBF particle group optimizing comprises:

Data preprocessing module, carries out pre-service for the model training sample will inputted from DCS database, to training sample centralization, namely deducts the mean value of sample, then carries out standardization to it:

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-th training sample, N is number of training, for the average of training sample, X is the training sample after standardization.σ _xrepresent the standard deviation of training sample, σ ² _xrepresent the variance of training sample.

Fuzzifying equation module, to the training sample X passed from data preprocessing module after the standardization of coming, carries out obfuscation.If have c in fuzzifying equation system ^*individual fuzzy group, the center of fuzzy group k, j is respectively v _k, v _j, then i-th training sample X after standardization _ifor the degree of membership μ of fuzzy group k _ikfor:

${\mathrm{\μ}}_{\mathrm{ik}}={\left(\underset{j=1}{\overset{c^{*}}{\mathrm{\Σ}}}{\left(\frac{\left|\right|X_i-v_k\left|\right|}{\left|\right|X_i-v_j\left|\right|}\right)}^{\frac{2}{n-1}}\right)}^{-1}---\left(4\right)$

In formula, n is the partitioned matrix index needed in fuzzy classification process, is usually taken as 2, || || be norm expression formula.

Use and be subordinate to angle value or its distortion to obtain new input matrix above, for fuzzy group k, its input matrix is deformed into:

Φ _ik(X _i,μ _ik)=[1func(μ _ik)X _i] （5）

Wherein func (μ _ik) for being subordinate to angle value μ _ikwarping function, generally get exp (μ _ik) etc., Φ _ik(X _i, μ _ik) represent i-th input variable X _iand the degree of membership μ of fuzzy group k _ikcorresponding new input matrix.

RBF neural, as the local equation of fuzzifying equation system, is optimized matching to each fuzzy group.If a kth RBF neural fuzzifying equation output be:

${\hat{y}}_{\mathrm{ik}}=\underset{l}{\mathrm{\Σ}}{w}_{\mathrm{lk}}{\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)---\left(6\right)$

Wherein C _lkand w _lkcenter and the output weights of a kth RBF neural fuzzifying equation l node, Φ _lk(|| X _i-C _lk||) be the radial basis function of a kth RBF neural fuzzifying equation l node, determined by following formula:

${\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)=\exp (-\frac{{\left(\right||X_i-C_{\mathrm{lk}})}^2}{2\×{\mathrm{\σ}}_{\mathrm{lk}}})---\left(7\right)$

Wherein σ _lkthe Gaussian width of corresponding radial basis function, || || be norm expression formula.Finally, the output of last fuzzifying equation system is obtained by the gravity model appoach in Anti-fuzzy method:

${\hat{y}}_i=\frac{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}{\hat{y}}_{\mathrm{ik}}}{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}}---\left(8\right)$

In formula, for a kth RBF neural fuzzifying equation output.

Particle cluster algorithm optimizes module, for adopting particle cluster algorithm to the C of RBF neural local equation in fuzzifying equation _pk, σ _pk, w _pkbe optimized, concrete steps are as follows:

1. determine that the Optimal Parameters of population is the C of RBF neural local equation _lk, σ _lk, w _lk, population individual amount popsize, largest loop optimizing number of times iter _max, a p particle initial position r _p, initial velocity v _p, local optimum Lbest _pand the global optimum Gbest of whole population.

2. set optimization object function, be converted into fitness, each On Local Fuzzy equation is evaluated; Calculate fitness function by corresponding error function, and think that the large particle fitness of error is little, the fitness function of particle p is expressed as:

f _p=1/(E _p+1) （9）

In formula, E _pbe the error function of fuzzifying equation system, be expressed as:

$E_p=\sqrt{\frac{1}{N}}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{({\hat{y}}_i-O_i)}^2---\left(10\right)$

In formula, the prediction output of fuzzifying equation system, O _ifor the target of fuzzifying equation system exports;

3. according to following formula, circulation upgrades speed and the position of each particle,

v _p(iter+1)=ω×v _p(iter)+m ₁a ₁(Lbest _p-r _p(iter))+m ₂a ₂(Gbest-r _p(iter))（11）

  

r _p(iter+1)=r _p(iter)+v _p(iter+1) （12）

In formula, v _prepresent the speed of more new particle p, r _prepresent the position of more new particle p, Lbest _prepresent the individual optimal value of more new particle p, Gbest is the global optimum of whole population, and iter represents cycle index, and ω is the inertia weight in particle cluster algorithm, m ₁, m ₂corresponding accelerator coefficient, a ₁, a ₂it is the random number between [0,1];

4. for particle p, if new fitness is greater than original individual optimal value, the more individual optimal value of new particle:

Lbest _p=f _p（13）

If the 5. individual optimal value Lbest of particle p _pbe greater than original population global optimum Gbest, upgrade original population global optimum Gbest:

Gbest=Lbest _p（14）

6. judge whether to meet performance requirement, if so, terminate optimizing, obtain the local equation parameter of the fuzzifying equation that a group is optimized; Otherwise return step 3., continue iteration optimizing, until reach maximum iteration time iter _max.

As preferred a kind of scheme, the industrial melt index soft measurement model of described RBF particle group optimizing also comprises: model modification module, for the online updating of model, is regularly input in training set by off-line analysis data, upgrades fuzzifying equation model.

An industrial melt index soft measuring method for RBF particle group optimizing, described flexible measurement method specific implementation step is as follows:

1), to propylene polymerization production process object, according to industrial analysis and Operations Analyst, select performance variable and easily survey the input of variable as model, performance variable and easily survey variable are obtained by DCS database;

2), by the model training sample inputted from DCS database carry out pre-service, to training sample centralization, namely deduct the mean value of sample, then carry out standardization to it, make its average be 0, variance is 1.This process adopts following formula process:

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

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

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

Wherein, TX _ibe i-th training sample, N is number of training, for the average of training sample, X is the training sample after standardization.σ _xrepresent the standard deviation of training sample, σ ² _xrepresent the variance of training sample.

3), to passing the training sample of coming from data preprocessing module, obfuscation is carried out.If have c in fuzzifying equation system ^*individual fuzzy group, the center of fuzzy group k, j is respectively v _k, v _j, then i-th training sample X after standardization _ifor the degree of membership μ of fuzzy group k _ikfor:

${\mathrm{\μ}}_{\mathrm{ik}}={\left(\underset{j=1}{\overset{c^{*}}{\mathrm{\Σ}}}{\left(\frac{\left|\right|X_i-v_k\left|\right|}{\left|\right|X_i-v_j\left|\right|}\right)}^{\frac{2}{n-1}}\right)}^{-1}---\left(4\right)$

In formula, n is the partitioned matrix index needed in fuzzy classification process, is usually taken as 2, || || be norm expression formula.

Use and be subordinate to angle value or its distortion to obtain new input matrix above, for fuzzy group k, its input matrix is deformed into:

Φ _ik(X _i,μ _ik)=[1func(μ _ik)X _i] （5）

Wherein func (μ _ik) for being subordinate to angle value μ _ikwarping function, generally get exp (μ _ik) etc., Φ _ik(X _i, μ _ik) represent i-th input variable X _iand the degree of membership of fuzzy group k _{μ ik}corresponding new input matrix.

RBF neural, as the local equation of fuzzifying equation system, is optimized matching to each fuzzy group.If a kth RBF neural fuzzifying equation output be:

${\hat{y}}_{\mathrm{ik}}=\underset{l}{\mathrm{\Σ}}{w}_{\mathrm{lk}}{\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)---\left(6\right)$

Wherein C _lkand w _lkcenter and the output weights of a kth RBF neural fuzzifying equation l node, Φ _lk(|| X _i-C _lk||) be the radial basis function of a kth RBF neural fuzzifying equation l node, determined by following formula:

${\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)=\exp (-\frac{{\left(\right||X_i-C_{\mathrm{lk}})}^2}{2\×{\mathrm{\σ}}_{\mathrm{lk}}})---\left(7\right)$

Wherein σ _lkthe Gaussian width of corresponding radial basis function, || || be norm expression formula.Finally, the output of last fuzzifying equation system is obtained by the gravity model appoach in Anti-fuzzy method:

${\hat{y}}_i=\frac{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}{\hat{y}}_{\mathrm{ik}}}{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}}---\left(8\right)$

In formula, for a kth RBF neural fuzzifying equation output.

4), adopt particle cluster algorithm to the C of RBF neural local equation in fuzzifying equation _pk, σ _pk, w _pkbe optimized, concrete steps are as follows:

1. determine that the Optimal Parameters of population is the C of RBF neural local equation _lk, σ _lk, w _lk, population individual amount popsize, largest loop optimizing number of times iter _max, a p particle initial position r _p, initial velocity v _p, local optimum Lbest _pand the global optimum Gbest of whole population.

2. set optimization object function, be converted into fitness, each On Local Fuzzy equation is evaluated; Calculate fitness function by corresponding error function, and think that the large particle fitness of error is little, the fitness function of particle p is expressed as:

f _p=1/(E _p+1) （9）

In formula, E _pbe the error function of fuzzifying equation system, be expressed as:

$E_p=\sqrt{\frac{1}{N}}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{({\hat{y}}_i-O_i)}^2---\left(10\right)$

In formula, the prediction output of fuzzifying equation system, O _ifor the target of fuzzifying equation system exports;

3. according to following formula, circulation upgrades speed and the position of each particle,

v _p(iter+1)=ω×v _p(iter)+m ₁a ₁(Lbest _p-r _p(iter))+m ₂a ₂(Gbest-r _p(iter))（11）

  

r _p(iter+1)=r _p(iter)+v _p(iter+1) （12）

In formula, v _prepresent the speed of more new particle p, r _prepresent the position of more new particle p, Lbest _prepresent the individual optimal value of more new particle p, Gbest is the global optimum of whole population, and iter represents cycle index, and ω is the inertia weight in particle cluster algorithm, m ₁, m ₂corresponding accelerator coefficient, a ₁, a ₂it is the random number between [0,1];

4. for particle p, if new fitness is greater than original individual optimal value, the more individual optimal value of new particle:

Lbest _p=f _p（13）

If the 5. individual optimal value Lbest of particle p _pbe greater than original population global optimum Gbest, upgrade original population global optimum Gbest:

Gbest=Lbest _p（14）

6. judge whether to meet performance requirement, if so, terminate optimizing, obtain the local equation parameter of the fuzzifying equation that a group is optimized; Otherwise return step 3., continue iteration optimizing, until reach maximum iteration time iter _max.

As preferred a kind of scheme: described flexible measurement method is further comprising the steps of: 5), be regularly input in training set by off-line analysis data, upgrade fuzzifying equation model.

Technical conceive of the present invention is: carry out online soft sensor to the important quality index melting index of propylene polymerization production process, overcome the deficiency that existing polypropylene melting index measurement instrument measuring accuracy is not high, low to noise sensitivity, promote poor performance, introduce particle cluster algorithm and Automatic Optimal is carried out to fuzzifying equation model, do not need artificial experience repeatedly to adjust the parameter of RBF neural local equation in fuzzifying equation.This soft measuring instrument, relative to existing melting index soft measuring instrument, has the following advantages:: (1) reduces noise and manual operation error to the impact of model prediction precision; (2) prediction performance of model is enhanced; (3) automatic optimal is carried out to the parameter of model, improve the stability of model, reduce the possibility that model is absorbed in local optimum.

Beneficial effect of the present invention is mainly manifested in: 1, on-line measurement; 2, on-line parameter Automatic Optimal; 3, model upgrades automatically; 4, anti-noise jamming ability strong, 5, precision is high.

Accompanying drawing explanation

Fig. 1 is the industrial melt index soft measurement instrument of RBF particle group optimizing and the basic structure schematic diagram of method;

Fig. 2 is the industrial melt index soft measurement model structural representation of RBF particle group optimizing.

Embodiment

Below in conjunction with accompanying drawing, the invention will be further described.The embodiment of the present invention is used for explaining and the present invention is described, instead of limits the invention, and in the protection domain of spirit of the present invention and claim, any amendment make the present invention and change, all fall into protection scope of the present invention.

Embodiment 1

With reference to Fig. 1, Fig. 2, a kind of industrial melt index soft measurement instrument of RBF particle group optimizing, comprise propylene polymerization production process 1, for measuring the field intelligent instrument 2 easily surveying variable, for measuring the control station 3 of performance variable, the DCS database 4 of store data and melt index flexible measured value display instrument 6, described field intelligent instrument 2, control station 3 is connected with propylene polymerization production process 1, described field intelligent instrument 2, control station 3 is connected with DCS database 4, described soft measuring instrument also comprises the soft-sensing model 5 that particle cluster algorithm optimizes RBF neural fuzzifying equation, described DCS database 4 is connected with the input end of the industrial melt index soft measurement model 5 of described RBF particle group optimizing, the output terminal of the industrial melt index soft measurement model 5 of described RBF particle group optimizing is connected with melt index flexible measured value display instrument 6, the industrial melt index soft measurement model of described RBF particle group optimizing comprises:

Data preprocessing module, carries out pre-service for the model training sample will inputted from DCS database, to training sample centralization, namely deducts the mean value of sample, then carries out standardization to it:

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-th training sample, N is number of training, for the average of training sample, X is the training sample after standardization.σ _xrepresent the standard deviation of training sample, σ ² _xrepresent the variance of training sample.

Fuzzifying equation module, to the training sample X passed from data preprocessing module after the standardization of coming, carries out obfuscation.If have c in fuzzifying equation system ^*individual fuzzy group, the center of fuzzy group k, j is respectively v _k, v _j, then i-th training sample X after standardization _ifor the degree of membership μ of fuzzy group k _ikfor:

${\mathrm{\μ}}_{\mathrm{ik}}={\left(\underset{j=1}{\overset{c^{*}}{\mathrm{\Σ}}}{\left(\frac{\left|\right|X_i-v_k\left|\right|}{\left|\right|X_i-v_j\left|\right|}\right)}^{\frac{2}{n-1}}\right)}^{-1}---\left(4\right)$

In formula, n is the partitioned matrix index needed in fuzzy classification process, is usually taken as 2, || || be norm expression formula.

Use and be subordinate to angle value or its distortion to obtain new input matrix above, for fuzzy group k, its input matrix is deformed into:

Φ _ik(X _i,μ _ik)=[1func(μ _ik)X _i] （5）

Wherein func (μ _ik) for being subordinate to angle value μ _ikwarping function, generally get exp (μ _ik) etc., Φ _ik(X _i, μ _ik) represent i-th input variable X _iand the degree of membership μ of fuzzy group k _ikcorresponding new input matrix.

RBF neural, as the local equation of fuzzifying equation system, is optimized matching to each fuzzy group.If a kth RBF neural fuzzifying equation output be:

${\hat{y}}_{\mathrm{ik}}=\underset{l}{\mathrm{\Σ}}{w}_{\mathrm{lk}}{\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)---\left(6\right)$

Wherein C _lkand w _lkcenter and the output weights of a kth RBF neural fuzzifying equation l node, Φ _lk(|| X _i-C _lk||) be the radial basis function of a kth RBF neural fuzzifying equation l node, determined by following formula:

${\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)=\exp (-\frac{{\left(\right||X_i-C_{\mathrm{lk}})}^2}{2\×{\mathrm{\σ}}_{\mathrm{lk}}})---\left(7\right)$

Wherein σ _lkthe Gaussian width of corresponding radial basis function, || || be norm expression formula.Finally, the output of last fuzzifying equation system is obtained by the gravity model appoach in Anti-fuzzy method:

${\hat{y}}_i=\frac{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}{\hat{y}}_{\mathrm{ik}}}{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}}---\left(8\right)$

In formula, for a kth RBF neural fuzzifying equation output.

Particle cluster algorithm optimizes module, for adopting particle cluster algorithm to the C of RBF neural local equation in fuzzifying equation _pk, σ _pk, w _pkbe optimized, specific implementation step is as follows:

1. determine that the Optimal Parameters of population is the C of RBF neural local equation _lk, σ _lk, w _lk, population individual amount popsize, largest loop optimizing number of times iter _max, a p particle initial position r _p, initial velocity v _p, local optimum Lbest _pand the global optimum Gbest of whole population.

2. set optimization object function, be converted into fitness, each On Local Fuzzy equation is evaluated; Calculate fitness function by corresponding error function, and think that the large particle fitness of error is little, the fitness function of particle p is expressed as:

f _p=1/(E _p+1) （9）

In formula, E _pbe the error function of fuzzifying equation system, be expressed as:

$E_p=\sqrt{\frac{1}{N}}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{({\hat{y}}_i-O_i)}^2---\left(10\right)$

In formula, the prediction output of fuzzifying equation system, O _ifor the target of fuzzifying equation system exports;

3. according to following formula, circulation upgrades speed and the position of each particle,

v _p(iter+1)=ω×v _p(iter)+m ₁a ₁(Lbest _p-r _p(iter))+m ₂a ₂(Gbest-r _p(iter))（11）

  

r _p(iter+1)=r _p(iter)+v _p(iter+1) （12）

In formula, v _prepresent the speed of more new particle p, r _prepresent the position of more new particle p, Lbest _prepresent the individual optimal value of more new particle p, Gbest is the global optimum of whole population, and iter represents cycle index, and ω is the inertia weight in particle cluster algorithm, m ₁, m ₂corresponding accelerator coefficient, a ₁, a ₂it is the random number between [0,1];

4. for particle p, if new fitness is greater than original individual optimal value, the more individual optimal value of new particle:

Lbest _p=f _p（13）

If the 5. individual optimal value Lbest of particle p _pbe greater than original population global optimum Gbest, upgrade original population global optimum Gbest:

Gbest=Lbest _p（14）

6. judge whether to meet performance requirement, if so, terminate optimizing, obtain the local equation parameter of the fuzzifying equation that a group is optimized; Otherwise return step 3., continue iteration optimizing, until reach maximum iteration time iter _max.

As preferred a kind of scheme, the industrial melt index soft measurement model of described RBF particle group optimizing also comprises: model modification module, for the online updating of model, is regularly input in training set by off-line analysis data, upgrades neural network model.

According to reaction mechanism and flow process analysis, consider in polypropylene production process the various factors that melting index has an impact, get nine performance variables conventional in actual production process and easily survey variable as modeling variable, have: three strand of third rare feed flow rates, major catalyst flow rate, cocatalyst flow rate, temperature in the kettle, pressure, liquid level, hydrogen volume concentration in still.Table 1 lists 9 the modeling variablees inputted as soft-sensing model 5, to be respectively in temperature in the kettle (T), still in pressure (p), still hydrogen volume concentration (X in liquid level (L), still _v), 3 bursts of propylene feed flow rates (first strand of third rare feed flow rates f1, second strand of third rare feed flow rates f2, the 3rd strand of third rare feed flow rates f3), 2 bursts of catalyst charge flow rates (major catalyst flow rate f4, cocatalyst flow rate f5).Polyreaction in reactor is that reaction mass mixes rear participation reaction repeatedly, and therefore mode input variable relates to the mean value in process variable employing front some moment of material.The data acquisition mean value of last hour in this example.Melting index off-line laboratory values is as the output variable of soft-sensing model 5.Obtained by hand sampling, off-line assay, within every 4 hours, analyze and gather once.

Field intelligent instrument 2 and control station 3 are connected with propylene polymerization production process 1, are connected with DCS database 4; Soft-sensing model 5 is connected with DCS database and hard measurement value display instrument 6.Field intelligent instrument 2 measures the easy survey variable that propylene polymerization produces object, is transferred to DCS database 4 by easily surveying variable; Control station 3 controls the performance variable that propylene polymerization produces object, performance variable is transferred to DCS database 4.In DCS database 4, the variable data of record is as the input of the industrial melt index soft measurement model 5 of RBF particle group optimizing, hard measurement value display instrument 6 for showing the output of the industrial melt index soft measurement model 5 of RBF particle group optimizing, i.e. hard measurement value.

Modeling variable needed for the industrial melt index soft measurement model of table 1:RBF particle group optimizing

Variable symbol	Variable implication	Variable symbol	Variable implication
				T	Temperature in the kettle	f1	First strand of third rare feed flow rates
p	Pressure in still	f2	Second strand of third rare feed flow rates
				L	Liquid level in still	f3	3rd strand of third rare feed flow rates
Xv	Hydrogen volume concentration in still	f4	Major catalyst flow rate
						f5	Cocatalyst flow rate

The industrial melt index soft measurement model 5 of RBF particle group optimizing, comprises following 4 parts:

Data preprocessing module 7, carries out pre-service for the model training sample will inputted from DCS database, to training sample centralization, namely deducts the mean value of sample, then carries out standardization to it:

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-th training sample, N is number of training, for the average of training sample, X is the training sample after standardization.σ _xrepresent the standard deviation of training sample, σ ² _xrepresent the variance of training sample.

Fuzzifying equation module 8, to the training sample X passed from data preprocessing module after the standardization of coming, carries out obfuscation.If have c in fuzzifying equation system ^*individual fuzzy group, the center of fuzzy group k, j is respectively v _k, v _j, then i-th training sample X after standardization _ifor the degree of membership μ of fuzzy group k _ikfor:

${\mathrm{\μ}}_{\mathrm{ik}}={\left(\underset{j=1}{\overset{c^{*}}{\mathrm{\Σ}}}{\left(\frac{\left|\right|X_i-v_k\left|\right|}{\left|\right|X_i-v_j\left|\right|}\right)}^{\frac{2}{n-1}}\right)}^{-1}---\left(4\right)$

In formula, n is the partitioned matrix index needed in fuzzy classification process, is usually taken as 2, || || be norm expression formula.

Use and be subordinate to angle value or its distortion to obtain new input matrix above, for fuzzy group k, its input matrix is deformed into:

Φ _ik(X _i,μ _ik)=[1func(μ _ik)X _i] （5）

Wherein func (μ _ik) for being subordinate to angle value μ _ikwarping function, generally get exp (μ _ik) etc., Φ _ik(X _i, μ _ik) represent i-th input variable X _iand the degree of membership μ of fuzzy group k _ikcorresponding new input matrix.

RBF neural, as the local equation of fuzzifying equation system, is optimized matching to each fuzzy group.If a kth RBF neural fuzzifying equation output be:

${\hat{y}}_{\mathrm{ik}}=\underset{l}{\mathrm{\Σ}}{w}_{\mathrm{lk}}{\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)---\left(6\right)$

Wherein C _lkand w _lkcenter and the output weights of a kth RBF neural fuzzifying equation l node, Φ _lk(|| X _i-C _lk||) be the radial basis function of a kth RBF neural fuzzifying equation l node, determined by following formula:

${\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)=\exp (-\frac{{\left(\right||X_i-C_{\mathrm{lk}})}^2}{2\×{\mathrm{\σ}}_{\mathrm{lk}}})---\left(7\right)$

Wherein σ _lkthe Gaussian width of corresponding radial basis function, || || be norm expression formula.Finally, the output of last fuzzifying equation system is obtained by the gravity model appoach in Anti-fuzzy method:

${\hat{y}}_i=\frac{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}{\hat{y}}_{\mathrm{ik}}}{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}}---\left(8\right)$

In formula, for a kth RBF neural fuzzifying equation output.

Particle cluster algorithm optimizes module 9, for adopting particle cluster algorithm to the C of RBF neural local equation in fuzzifying equation _pk, σ _pk, w _pkbe optimized, specific implementation step is as follows:

1. determine that the Optimal Parameters of population is the C of RBF neural local equation _lk, σ _lk, w _lk, population individual amount popsize, largest loop optimizing number of times iter _max, a p particle initial position r _p, initial velocity v _p, local optimum Lbest _pand the global optimum Gbest of whole population.

2. set optimization object function, be converted into fitness, each On Local Fuzzy equation is evaluated; Calculate fitness function by corresponding error function, and think that the large particle fitness of error is little, the fitness function of particle p is expressed as:

f _p=1/(E _p+1) （9）

In formula, E _pbe the error function of fuzzifying equation system, be expressed as:

$E_p=\sqrt{\frac{1}{N}}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{({\hat{y}}_i-O_i)}^2---\left(10\right)$

In formula, the prediction output of fuzzifying equation system, O _ifor the target of fuzzifying equation system exports;

3. according to following formula, circulation upgrades speed and the position of each particle,

v _p(iter+1)=ω×v _p(iter)+m ₁a ₁(Lbest _p-r _p(iter))+m ₂a ₂(Gbest-r _p(iter))（11）

   

r _p(iter+1)=r _p(iter)+v _p(iter+1) （12）

In formula, v _prepresent the speed of more new particle p, r _prepresent the position of more new particle p, Lbest _prepresent the individual optimal value of more new particle p, Gbest is the global optimum of whole population, and iter represents cycle index, and ω is the inertia weight in particle cluster algorithm, m ₁, m ₂corresponding accelerator coefficient, a ₁, a ₂it is the random number between [0,1];

4. for particle p, if new fitness is greater than original individual optimal value, the more individual optimal value of new particle:

Lbest _p=f _p（13）

If the 5. individual optimal value Lbest of particle p _pbe greater than original population global optimum Gbest, upgrade original population global optimum Gbest:

Gbest=Lbest _p（14）

6. judge whether to meet performance requirement, if so, terminate optimizing, obtain the local equation parameter of the fuzzifying equation that a group is optimized; Otherwise return step 3., continue iteration optimizing, until reach maximum iteration time iter _max.

Model modification module 10, for the online updating of model, is regularly input in training set by off-line analysis data, upgrades fuzzifying equation model.

Embodiment 2

With reference to Fig. 1, Fig. 2, a kind of industrial polypropylene producing melt index flexible measurement method optimizing RBF neural fuzzifying equation model based on particle cluster algorithm, described flexible measurement method specific implementation step is as follows:

1), to propylene polymerization production process object, according to industrial analysis and Operations Analyst, select performance variable and easily survey the input of variable as model, performance variable and easily survey variable are obtained by DCS database;

2), by the model training sample inputted from DCS database carry out pre-service, to training sample centralization, namely deduct the mean value of sample, then carry out standardization to it, make its average be 0, variance is 1.This process adopts following formula process:

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

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

2.3) standardization: $X=\frac{\mathrm{TX}-\stackrel{\‾}{\mathrm{TX}}}{{\mathrm{\σ}}_x}---\left(3\right)$ Wherein, TX _ibe i-th training sample, N is number of training, for the average of training sample, X is the training sample after standardization.σ _xrepresent the standard deviation of training sample, σ ² _xrepresent the variance of training sample.

3), to passing the training sample after standardization of coming from data preprocessing module, obfuscation is carried out.If have c in fuzzifying equation system ^*individual fuzzy group, the center of fuzzy group k, j is respectively v _k, v _j, then i-th training sample X after standardization _ifor the degree of membership μ of fuzzy group k _ikfor:

${\mathrm{\μ}}_{\mathrm{ik}}={\left(\underset{j=1}{\overset{c^{*}}{\mathrm{\Σ}}}{\left(\frac{\left|\right|X_i-v_k\left|\right|}{\left|\right|X_i-v_j\left|\right|}\right)}^{\frac{2}{n-1}}\right)}^{-1}---\left(4\right)$

In formula, n is the partitioned matrix index needed in fuzzy classification process, is usually taken as 2, || || be norm expression formula.

Use and be subordinate to angle value or its distortion to obtain new input matrix above, for fuzzy group k, its input matrix is deformed into:

Φ _ik(X _i,μ _ik)=[1func(μ _ik)X _i] （5）

Wherein func (μ _ik) for being subordinate to angle value μ _ikwarping function, generally get exp (μ _ik) etc., Φ _ik(X _i, μ _ik) represent i-th input variable X _iand the degree of membership μ of fuzzy group k _ikcorresponding new input matrix.

RBF neural, as the local equation of fuzzifying equation system, is optimized matching to each fuzzy group.If a kth RBF neural fuzzifying equation output be:

${\hat{y}}_{\mathrm{ik}}=\underset{l}{\mathrm{\Σ}}{w}_{\mathrm{lk}}{\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)---\left(6\right)$

Wherein C _lkand w _lkcenter and the output weights of a kth RBF neural fuzzifying equation l node, Φ _lk(|| X _i-C _lk||) be the radial basis function of a kth RBF neural fuzzifying equation l node, determined by following formula:

${\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)=\exp (-\frac{{\left(\right||X_i-C_{\mathrm{lk}})}^2}{2\×{\mathrm{\σ}}_{\mathrm{lk}}})---\left(7\right)$

Wherein σ _lkthe Gaussian width of corresponding radial basis function, || || be norm expression formula.Finally, the output of last fuzzifying equation system is obtained by the gravity model appoach in Anti-fuzzy method:

${\hat{y}}_i=\frac{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}{\hat{y}}_{\mathrm{ik}}}{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}}---\left(8\right)$

In formula, for a kth RBF neural fuzzifying equation output.

4), adopt particle cluster algorithm to the C of RBF neural local equation in fuzzifying equation _pk, σ _pk, w _pkbe optimized, specific implementation step is as follows:

1. determine that the Optimal Parameters of population is the C of RBF neural local equation _lk, σ _lk, w _lk, population individual amount popsize, largest loop optimizing number of times iter _max, a p particle initial position r _p, initial velocity v _p, local optimum Lbest _pand the global optimum Gbest of whole population.

2. set optimization object function, be converted into fitness, each On Local Fuzzy equation is evaluated; Calculate fitness function by corresponding error function, and think that the large particle fitness of error is little, the fitness function of particle p is expressed as:

f _p=1/(E _p+1) （9）

In formula, E _pbe the error function of fuzzifying equation system, be expressed as:

$E_p=\sqrt{\frac{1}{N}}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{({\hat{y}}_i-O_i)}^2---\left(10\right)$

In formula, the prediction output of fuzzifying equation system, O _ifor the target of fuzzifying equation system exports;

3. according to following formula, circulation upgrades speed and the position of each particle,

v _p(iter+1)=ω×v _p(iter)+m ₁a ₁(Lbest _p-r _p(iter))+m ₂a ₂(Gbest-r _p(iter))（11）

   

r _p(iter+1)=r _p(iter)+v _p(iter+1) （12）

In formula, v _prepresent the speed of more new particle p, r _prepresent the position of more new particle p, Lbest _prepresent the individual optimal value of more new particle p, Gbest is the global optimum of whole population, and iter represents cycle index, and ω is the inertia weight in particle cluster algorithm, m ₁, m ₂corresponding accelerator coefficient, a ₁, a ₂it is the random number between [0,1];

4. for particle p, if new fitness is greater than original individual optimal value, the more individual optimal value of new particle:

Lbest _p=f _p（13）

If the 5. individual optimal value Lbest of particle p _pbe greater than original population global optimum Gbest, upgrade original population global optimum Gbest:

Gbest=Lbest _p（14）

6. judge whether to meet performance requirement, if so, terminate optimizing, obtain the local equation parameter of the fuzzifying equation that a group is optimized; Otherwise return step 3., continue iteration optimizing, until reach maximum iteration time iter _max.

As preferred a kind of scheme: described flexible measurement method is further comprising the steps of: 5), be regularly input in training set by off-line analysis data, upgrade fuzzifying equation model.

The concrete implementation step of method of the present embodiment is as follows:

Step 1: to propylene polymerization production process object 1, according to industrial analysis and Operations Analyst, selects performance variable and easily surveys the input of variable as model.Performance variable and easily survey variable are obtained by DCS database 4.

Step 2: carry out pre-service to sample data, is completed by data preprocessing module 7.

Step 3: set up initial fuzzy equation model 8 based on model training sample data.Input data obtain as described in step 2, export data and chemically examine acquisition by off-line.

Step 4: the local RBF neural equation parameter being optimized initial fuzzy equation model 8 by particle cluster algorithm 9.

Step 5: off-line analysis data is regularly input in training set by model modification module 10, upgrades fuzzifying equation model, and the soft-sensing model 5 optimizing RBF neural fuzzifying equation model based on particle cluster algorithm has been set up.

Step 6: melt index flexible measured value display instrument 6 shows the output of the industrial melt index soft measurement model 5 of RBF particle group optimizing, completes the display of measuring industrial polypropylene producing melt index flexible.

Claims (2)

1. the industrial melt index soft measurement instrument of a RBF particle group optimizing, comprise for measuring the field intelligent instrument easily surveying variable, for measuring the control station of performance variable, the DCS database of store data and melt index flexible measured value display instrument, described field intelligent instrument, control station is connected with DCS database, it is characterized in that: described soft measuring instrument also comprises the industrial melt index soft measurement model of RBF particle group optimizing, described DCS database is connected with the input end of the industrial melt index soft measurement model of described RBF particle group optimizing, the output terminal of the industrial melt index soft measurement model of described RBF particle group optimizing is connected with melt index flexible measured value display instrument, the industrial melt index soft measurement model of described RBF particle group optimizing comprises:

Data preprocessing module, carries out pre-service for the model training sample will inputted from DCS database, to training sample centralization, namely deducts the mean value of sample, then carries out standardization to it:

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-th training sample, N is number of training, for the average of training sample, X is the training sample after standardization; σ _xrepresent the standard deviation of training sample, σ ² _xrepresent the variance of training sample;

Fuzzifying equation module, to the training sample X passed from data preprocessing module after the standardization of coming, carries out obfuscation; If have c in fuzzifying equation system ^*individual fuzzy group, the center of fuzzy group k, j is respectively v _k, v _j, then i-th training sample X after standardization _ifor the degree of membership μ of fuzzy group k _ikfor:

${\mathrm{\μ}}_{\mathrm{ik}}={\left(\underset{j=1}{\overset{c^{*}}{\mathrm{\Σ}}}{\left(\frac{\left|\right|X_i-v_k\left|\right|}{\left|\right|X_i-v_j\left|\right|}\right)}^{\frac{2}{n-1}}\right)}^{-1}---\left(4\right)$

In formula, n is the partitioned matrix index needed in fuzzy classification process, is taken as 2, || || be norm expression formula;

Use and be subordinate to angle value or its distortion to obtain new input matrix above, for fuzzy group k, its input matrix is deformed into:

Φ _ik(X _i,μ _ik)＝[1 func(μ _ik) X _i] (5)

Wherein func (μ _ik) for being subordinate to angle value μ _ikwarping function, get or exp (μ _ik), Φ _ik(X _i, μ _ik) represent i-th training sample X after standardization _iand the degree of membership μ of fuzzy group k _ikcorresponding new input matrix;

RBF neural, as the local equation of fuzzifying equation system, is optimized matching to each fuzzy group; If the output of a kth RBF neural fuzzifying equation is:

${\hat{y}}_{\mathrm{ik}}=\underset{l}{\mathrm{\Σ}}{w}_{\mathrm{lk}}{\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)---\left(6\right)$

Wherein C _lkand w _lkcenter and the output weights of a kth RBF neural fuzzifying equation l node, Φ _lk(|| X _i-C _lk||) be the radial basis function of a kth RBF neural fuzzifying equation l node, determined by following formula:

${\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)=\exp (-\frac{{({\left|\right|X}_i-C_{\mathrm{lk}}|\left|\right)}^2}{2\×{\mathrm{\σ}}_{\mathrm{lk}}})---\left(7\right)$

Wherein σ _lkthe Gaussian width of corresponding radial basis function, || || be norm expression formula; Finally, the output of last fuzzifying equation system is obtained by the gravity model appoach in Anti-fuzzy method:

${\hat{y}}_i=\frac{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}{\hat{y}}_{\mathrm{ik}}}{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}}---\left(8\right)$

In formula, for a kth RBF neural fuzzifying equation output;

Particle cluster algorithm optimizes module, for adopting particle cluster algorithm to the C of RBF neural local equation in fuzzifying equation _pk, σ _pk, w _pkbe optimized, specific implementation step is as follows:

1. determine that the Optimal Parameters of population is the C of RBF neural local equation _pk, σ _pk, w _pk, population individual amount popsize, largest loop optimizing number of times iter _max, a p particle initial position r _p0, initial velocity v _p0, local optimum Lbest _p0and the global optimum Gbest of whole population;

2. set optimization object function, be converted into fitness, the output of each fuzzifying equation system is evaluated; Calculate fitness function by corresponding error function, and think that the large particle fitness of error is little, the fitness function of particle p is expressed as:

f _p＝1/(E _p+1) (9)

In formula, E _pbe the error function of fuzzifying equation system, be expressed as:

$E_p=\sqrt{\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{({\hat{y}}_i-O_i)}^2}---\left(10\right)$

In formula, the output of fuzzifying equation system, O _ifor the target of fuzzifying equation system exports;

3. according to following formula, circulation upgrades speed and the position of each particle,

v _p(iter+1)＝ω×v _p(iter)+m ₁a ₁(Lbest _p-r _p(iter))+m ₂a ₂(Gbest-r _p(iter))

(11)

r _p(iter+1)＝r _p(iter)+v _p(iter+1) (12)

In formula, v _prepresent the speed of more new particle p, r _prepresent the position of more new particle p, Lbest _prepresent the individual optimal value of more new particle p, iter represents cycle index, and ω is the inertia weight in particle cluster algorithm, m ₁, m ₂corresponding accelerator coefficient, a ₁, a ₂it is the random number between [0,1];

4. for particle p, if new fitness is greater than original individual optimal value, the more individual optimal value of new particle:

Lbest _p＝f _p(13)

If the 5. individual optimal value Lbest of particle p _pbe greater than original population global optimum Gbest, upgrade original population global optimum Gbest:

Gbest＝Lbest _p(14)

6. judge whether to meet performance requirement, if so, terminate optimizing, obtain the local equation parameter of the fuzzifying equation that a group is optimized; Otherwise return step 3., continue iteration optimizing, until reach largest loop optimizing number of times iter _max;

The industrial melt index soft measurement model of described RBF particle group optimizing also comprises:

Model modification module, for the online updating of model, is regularly input in training set by off-line analysis data, upgrades fuzzifying equation model.

2., with the flexible measurement method that the industrial melt index soft measurement instrument of RBF particle group optimizing as claimed in claim 1 realizes, it is characterized in that: described flexible measurement method specific implementation step is as follows:

1), to propylene polymerization production process object, according to industrial analysis and Operations Analyst, select performance variable and easily survey the input of variable as model, performance variable and easily survey variable are obtained by DCS database;

2), by the model training sample inputted from DCS database carry out pre-service, to training sample centralization, namely deduct the mean value of sample, then carry out standardization to it, make its average be 0, variance is 1; This process adopts following formula process:

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

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

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

Wherein, TX _ibe i-th training sample, N is number of training, for the average of training sample, X is the training sample after standardization; σ _xrepresent the standard deviation of training sample, σ ² _xrepresent the variance of training sample;

3), to passing the training sample of coming from data preprocessing module, obfuscation is carried out; If have c in fuzzifying equation system ^*individual fuzzy group, the center of fuzzy group k, j is respectively v _k, v _j, then i-th training sample X after standardization _ifor the degree of membership μ of fuzzy group k _ikfor:

${\mathrm{\μ}}_{\mathrm{ik}}={\left(\underset{j=1}{\overset{c^{*}}{\mathrm{\Σ}}}{\left(\frac{\left|\right|X_i-v_k\left|\right|}{\left|\right|X_i-v_j\left|\right|}\right)}^{\frac{2}{n-1}}\right)}^{-1}---\left(4\right)$

In formula, n is the partitioned matrix index needed in fuzzy classification process, is taken as 2, || || be norm expression formula;

Use and be subordinate to angle value or its distortion to obtain new input matrix above, for fuzzy group k, its input matrix is deformed into:

Φ _ik(X _i,μ _ik)＝[1 func(μ _ik) X _i] (5)

Wherein func (μ _ik) for being subordinate to angle value μ _ikwarping function, get or exp (μ _ik), Φ _ik(X _i, μ _ik) represent i-th training sample X after standardization _iand the degree of membership μ of fuzzy group k _ikcorresponding new input matrix;

RBF neural, as the local equation of fuzzifying equation system, is optimized matching to each fuzzy group; If the output of a kth RBF neural fuzzifying equation is:

${\hat{y}}_{\mathrm{ik}}=\underset{l}{\mathrm{\Σ}}{w}_{\mathrm{lk}}{\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)---\left(6\right)$

Wherein C _lkand w _lkcenter and the output weights of a kth RBF neural fuzzifying equation l node, Φ _lk(|| X _i-C _lk||) be the radial basis function of a kth RBF neural fuzzifying equation l node, determined by following formula:

${\mathrm{\Φ}}_{\mathrm{lk}}\left(\right||X_i-C_{\mathrm{lk}}|\left|\right)=\exp (-\frac{{({\left|\right|X}_i-C_{\mathrm{lk}}|\left|\right)}^2}{2\×{\mathrm{\σ}}_{\mathrm{lk}}})---\left(7\right)$

Wherein σ _lkthe Gaussian width of corresponding radial basis function, || || be norm expression formula; Finally, the output of last fuzzifying equation system is obtained by the gravity model appoach in Anti-fuzzy method:

${\hat{y}}_i=\frac{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}{\hat{y}}_{\mathrm{ik}}}{{\mathrm{\Σ}}_{k=1}^{c^{*}}{\mathrm{\μ}}_{\mathrm{ik}}}---\left(8\right)$

In formula, for a kth RBF neural fuzzifying equation output;

4), adopt particle cluster algorithm to the C of RBF neural local equation in fuzzifying equation _pk, σ _pk, w _pkbe optimized, specific implementation step is as follows:

1. determine that the Optimal Parameters of population is the C of RBF neural local equation _pk, σ _pk, w _pk, population individual amount popsize, largest loop optimizing number of times iter _max, a p particle initial position r _p0, initial velocity v _p0, local optimum Lbest _p0and the global optimum Gbest of whole population;

2. set optimization object function, be converted into fitness, the output of each fuzzifying equation system is evaluated; Calculate fitness function by corresponding error function, and think that the large particle fitness of error is little, the fitness function of particle p is expressed as:

f _p＝1/(E _p+1) (9)

In formula, E _pbe the error function of fuzzifying equation system, be expressed as:

$E_p=\sqrt{\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{({\hat{y}}_i-O_i)}^2}---\left(10\right)$

In formula, the output of fuzzifying equation system, O _ifor the target of fuzzifying equation system exports;

3. according to following formula, circulation upgrades speed and the position of each particle,

v _p(iter+1)＝ω×v _p(iter)+m ₁a ₁(Lbest _p-r _p(iter))+m ₂a ₂(Gbest-r _p(iter))

(11)

r _p(iter+1)＝r _p(iter)+v _p(iter+1) (12)

In formula, v _prepresent the speed of more new particle p, r _prepresent the position of more new particle p, Lbest _prepresent the individual optimal value of more new particle p, iter represents cycle index, and ω is the inertia weight in particle cluster algorithm, m ₁, m ₂corresponding accelerator coefficient, a ₁, a ₂it is the random number between [0,1];

4. for particle p, if new fitness is greater than original individual optimal value, the more individual optimal value of new particle:

Lbest _p＝f _p(13)

If the 5. individual optimal value Lbest of particle p _pbe greater than original population global optimum Gbest, upgrade original population global optimum Gbest:

Gbest＝Lbest _p(14)

6. judge whether to meet performance requirement, if so, terminate optimizing, obtain the local equation parameter of the fuzzifying equation that a group is optimized; Otherwise return step 3., continue iteration optimizing, until reach largest loop optimizing number of times iter _max;

Described flexible measurement method is further comprising the steps of: 5), be regularly input in training set by off-line analysis data, upgrades fuzzifying equation model.