CN101017374A - Polypropylene melting index softsensoring instrument based on blind signal analysis and method thereof - Google Patents

Abstract

This invention relate to one Poly Propylene melt index flexible measurement meter based on blind source signals, which comprises poly propylene process subject connection spot intelligent meter, data memory device and upper machine to store historical data, intelligent meter, data memory device and upper machine, wherein, the upper machine is for flexible intelligent processor composed of standard process module, blind source signal analysis module, supportive vector machine establish module, signal collection module and flexible module. This invention provides one flexible measure method.

Description

Polypropylene melt index soft measuring instrument and method based on blind signal analysis

(1) technical field

The present invention relates to the soft fields of measurement of industrial process, especially, relate to a kind of polypropylene melting index soft measuring instrument and method based on blind signal analysis.

(2) background technology

Polypropylene is to be the main a kind of synthetic resin that is polymerized with the propylene monomer, is the staple product in the plastics industry.In the polyolefin resin of present China, become the third-largest plastics that are only second to tygon and Polyvinylchloride.In polypropylene production process, melting index (MI) is an important indicator of reflection product quality.But MI can only offline inspection, and is expensive and consuming time, can't in time understand the state of polypropylene production process.Therefore, choose with the closely-related easy survey variable of melting index as secondary variable, therefrom analyze melting index, whether normal, become the difficult point and the key of current propylene polymerization production process if detecting production run.

(3) summary of the invention

For overcome existing polypropylene melting index measurement instrument can only off-line measurement, computing velocity is slow, whether can not detect production run in real time normal not enough, the invention provides a kind of can on-line measurement, computing velocity is fast, and can detect the polypropylene melting index soft measuring instrument and the method based on blind signal analysis of production run in real time.

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

A kind of polypropylene melting index soft measuring instrument based on blind signal analysis, comprise the field intelligent instrument that is connected with the polypropylene production process object, the data storage device that is used for storing history data and host computer, intelligence instrument, data storage device and host computer link to each other successively, described host computer is soft measurement intelligent processor, and described soft measurement intelligent processor comprises:

The standardization module is used for data are carried out standardization, makes that the average of each variable is 0, and variance is 1, obtains input matrix X, adopts following process to finish, and its formula is (1), (2), (3):

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

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

Wherein, TX is a training sample, and N is a number of training,

Average for training sample;

The blind signal analysis module is used for according to the blind source signal number of extracting, and extracts mutually independently blind source signal from input variable, and concrete steps are as follows:

1) choosing norm is 1 initial weight vector (at random) w _i, if i 〉=2, then $w_i=w_i-W_{i-1}{W}_{i-1}^T{w}_i,$ W wherein _I-1=[w ₁w ₂L w _L-1], i=1 ..., m;

2) to w _iCarrying out iteration upgrades: $w_i^{+}=E\left\{\mathrm{xg}\left(w_i^{T}x\right)\right\}-E\{g\text{'}\left(w_i^{T}x\right)\}{w}_i,$ W wherein _i ⁺

Weight vectors after expression is upgraded, E is a mathematical expectation, g (u)=uexp (u ²/ 2);

3) standardization $w_i=w_i^{+}/\left|\right|w_i^{+}\left|\right|,$ ‖ w wherein _i ⁺‖ represents w _i ⁺Norm;

4) if do not restrain, return 2; Otherwise iteration is to i=m always;

Wherein the condition of convergence is the w of renewal _iWith former w _iDot product is 1, thereby blind source signal can be calculated by S=WX;

The support vector machine MBM is used for according to the support vector machine nuclear parameter, calculates kernel function, and concrete steps are as follows:

Find the solution following quadratic programming problem, its formula is (4):

$\underset{{\mathrm{\α},\mathrm{\α}}^{*}}{\max }\{L_D=-\frac{1}{2}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}\underset{j=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})({\mathrm{\α}}_j-{\mathrm{\α}}_j^{*})K(x_i,x_j)-\mathrm{\ϵ}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i+{\mathrm{\α}}_i^{*})+\underset{i=1}{\overset{M}{\mathrm{\Σ}}}{y}_i({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})\}---\left(4\right)$

$s.t.\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})=0$

0≤α _i≤γ

0≤α _i ^*≤γ

Calculate w thus and treat estimation function f (x), its formula is (5):

Wherein, α _i(i=1 ..., N) be the Lagrange multiplier, x _i(i=1 ..., N) be input vector, y is an output variable, ω is the normal vector of support vector machine lineoid, the direction of decision lineoid, the position of b decision lineoid;

Signal acquisition module is used to set time interval of each sampling, image data from database; Soft measurement module is used for data to be tested VX the time is obtained with training

And δ _x ²Carry out standardization, and with the data after the standardization through the blind signal analysis resume module that obtains of training after as the input of support vector machine MBM, the supporting vector machine model with input substitution training obtains obtains soft measurement functions value.

As preferred a kind of scheme: described soft measurement intelligent processor also comprises: the model modification module, be used for regularly the real data of offline inspection is added to training set, and upgrade supporting vector machine model.

As preferred another kind of scheme: described soft measuring instrument also comprises the DCS system, described DCS system is made of data-interface, control station and historical data base, described data storage device is the historical data base of DCS system, described soft measurement intelligent processor also comprises: display module as a result, be used for soft measurement result is passed to the DCS system, show at the control station of DCS, and be delivered to operator station by DCS system and fieldbus and show.

As preferred another scheme: described field intelligent instrument, DCS system, soft measurement intelligent processor connect successively by fieldbus.

The described flexible measurement method of realizing based on the polypropylene melting index soft measuring instrument of blind signal analysis of a kind of usefulness, described flexible measurement method may further comprise the steps:

(1), determine the key variables that soft measurement is used, from historical data base acquisition system just often the data of described variable as training sample TX;

(2), the extraction blind source signal number of blind signal analysis module, the nuclear parameter of support vector machine MBM and setting sampling period are set;

(3), training sample TX in soft measurement intelligent processor, data are carried out standardization, make that the average of each variable is 0, variance is 1, obtains input matrix X, adopts following process to finish, its formula is (1), (2), (3):

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

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

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

Wherein, TX is a training sample, and N is a number of training,

Average for training sample;

(4), again data are carried out blind signal analysis, concrete steps are:

4.1) to choose norm be 1 initial weight vector (at random) w _i, if i 〉=2, then $w_i=w_i-W_{i-1}{W}_{i-1}^T{w}_i,$

W wherein _I-1=[w ₁w ₂L w _I-1], i=1 ..., m;

4.2) to w _iCarrying out iteration upgrades: $w_i^{+}=E\left\{\mathrm{xg}\left(w_i^{T}x\right)\right\}-E\{g\text{'}\left(w_i^{T}x\right)\}{w}_i;$

4.3) standardization $w_i=w_i^{+}/\left|\right|w_i^{+}\left|\right|;$

4.4) if do not restrain, return 2.Otherwise iteration is to i=m always;

Wherein the condition of convergence is the w of renewal _iWith former w _iDot product is 1, and blind source signal is calculated by S=WX;

(5), with blind source signal as the input of institute's established model, set up supporting vector machine model, promptly find the solution following quadratic programming problem, its formula is (4):

$\underset{{\mathrm{\α},\mathrm{\α}}^{*}}{\max }\{L_D=-\frac{1}{2}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}\underset{j=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})({\mathrm{\α}}_j-{\mathrm{\α}}_j^{*})K(x_i,x_j)-\mathrm{\ϵ}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i+{\mathrm{\α}}_i^{*})+\underset{i=1}{\overset{M}{\mathrm{\Σ}}}{y}_i({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})\}---\left(4\right)$

$s.t.\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})=0$

0≤α _i≤γ

0≤α _i ^*≤γ

Can get w thus and treat estimation function f (x), its formula is (5):

(6), the data of gathering are sent in the data storage device, from the real-time data base of data storage device, obtain up-to-date variable data at each timing cycle as data VX to be measured; VX the time is obtained with training

And δ _x ²Carry out standardization, and with the input of the data after the standardization as model, the supporting vector machine model with input substitution training obtains obtains soft measurement functions value.

As preferred a kind of scheme: described flexible measurement method also comprises: (7), regularly the real data with offline inspection is added in the training set, to upgrade supporting vector machine model.

As preferred another kind of scheme: described data storage device is the historical data base of DCS system, described DCS system is made of data-interface, control station and historical data base, in described (6), calculate soft measured value, the result is passed to the DCS system, show at the control station of DCS, and be delivered to operator station by DCS system and fieldbus and show.

Technical conceive of the present invention is: utilize industrial measured data, adopt the method for statistics to carry out fault diagnosis, avoided complicated Analysis on Mechanism, it is convenient relatively to find the solution.Blind signal analysis (ICA) is a kind of signal processing method based on high-order statistic, use it for the process data analyzing and processing of process industry, can more effectively utilize the probabilistic statistical characteristics of variable, can under the statistics independent meaning, decompose observational variable, obtain the activation bit source of process inherence, thereby more constitutionally is described process feature, and is more accurate, more reliable to the modeling of process.

More effectively utilize the probabilistic statistical characteristics of variable, thereby more constitutionally is described process feature, improve model accuracy.

Beneficial effect of the present invention mainly shows: the decorrelation sexuality of blind signal analysis and the multivariable nonlinearity mapping ability and the strong generalization ability of support vector machine are combined well, brought into play advantage separately, make that the model of being set up is effectively reliable more, can better instruct production, improve productivity effect.

(4) description of drawings

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

Fig. 2 is the functional block diagram of soft measurement intelligent processor proposed by the invention;

Fig. 3 is a polypropylene production procedure sketch.

(5) embodiment

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

Embodiment 1

With reference to Fig. 1, Fig. 2 and Fig. 3, a kind of polypropylene melting index soft measuring instrument based on blind signal analysis, comprise the field intelligent instrument 2 that is connected with polypropylene production process object 1, the data storage device 5 that is used for storing history data and host computer 6, intelligence instrument 1, data storage device 5 and host computer 5 link to each other successively, described host computer 6 is soft measurement intelligent processor, and described soft measurement intelligent processor comprises:

Standardization module 7 is used for database acquisition system data are just often carried out standardization, and the average of each variable is 0, and variance is 1, obtains input matrix X, adopts following process to finish:

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

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

Wherein, TX is a training sample, and N is a number of training,

Average for training sample;

Blind signal analysis module 8 is used for according to the blind source signal number of extracting, and extracts mutually independently blind source signal from input variable, and concrete steps are as follows:

1) choosing norm is 1 initial weight vector (at random) w _i, if i 〉=2, then $w_i=w_i-W_{i-1}{W}_{i-1}^T{w}_i,$ W wherein _I-1=[w ₁w ₂L w _I-1], i=1 ..., m;

2) to w _iCarrying out iteration upgrades: $w_i^{+}=E\left\{\mathrm{xg}\left(w_i^{T}x\right)\right\}-E\{g\text{'}\left(w_i^{T}x\right)\}{w}_i,$ W wherein _i ⁺

Weight vectors after expression is upgraded, E is a mathematical expectation, g (u)=uexp (u ²/ 2);

3) standardization $w_i=w_i^{+}/\left|\right|w_i^{+}\left|\right|,$ ‖ w wherein _i ⁺‖ represents w _i ⁺Norm;

4) if do not restrain, return 2.Otherwise iteration is to i=m always;

Wherein the condition of convergence is the w of renewal _iWith former w _iDot product is 1, thereby blind source signal can be counted by S=WX

Obtain;

Support vector machine MBM 9 is used for according to the support vector machine nuclear parameter, calculates kernel function, and concrete steps are as follows:

Find the solution following quadratic programming problem, its formula is (4):

$\underset{{\mathrm{\α},\mathrm{\α}}^{*}}{\max }\{L_D=-\frac{1}{2}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}\underset{j=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})({\mathrm{\α}}_j-{\mathrm{\α}}_j^{*})K(x_i,x_j)-\mathrm{\ϵ}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i+{\mathrm{\α}}_i^{*})+\underset{i=1}{\overset{M}{\mathrm{\Σ}}}{y}_i({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})\}---\left(4\right)$

$s.t\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})=0$

0≤α _i≤γ

0≤α _i ^*≤γ

Calculate w thus and treat estimation function f (x), its formula is (5):

Wherein, α _i(i=1 ..., N) be the Lagrange multiplier, x _i(i=1 ..., N) be input vector, y is an output variable, ω is the normal vector of support vector machine lineoid, the direction of decision lineoid, the position of b decision lineoid;

Signal acquisition module 10 is used to set time interval of each sampling, image data from database;

Soft measurement module 11 is used for data to be tested VX the time is obtained with training And δ _x ²Carry out standardization, and with the data after the standardization through the blind signal analysis resume module that obtains of training after as the input of support vector machine MBM, the supporting vector machine model with input substitution training obtains obtains soft measurement functions value.

Described soft measurement intelligent processor 6 also comprises: model modification module 12 is used for regular real data with offline inspection and is added to training set, to upgrade supporting vector machine model.

Soft measuring instrument also comprises the system with DCS, and described DCS system is made of data-interface 3, control station 4, database 5; Intelligence instrument 2, DCS system, host computer 6 link to each other successively by fieldbus, described host computer also comprises: display module 13 as a result, be used for soft measurement result is passed to the DCS system, and, by DCS system and fieldbus process status information is delivered to operator station simultaneously and shows at the control station procedure for displaying state of DCS.

The hardware components of described intelligent processor 6 comprises: the I/O element is used for the collection of data and the transmission of information; Data-carrier store, data sample that storage running is required and operational factor etc.; Program storage, storage realizes the software program of functional module; Arithmetical unit, executive routine, the function of realization appointment; Display module shows the parameter and the operation result that are provided with.

When soft measuring instrument process to be detected has been furnished with the DCS system, the real-time and historical data base of the detection of sample real-time dynamic data, memory by using DCS system, soft measurement function is mainly finished on host computer.

When soft measuring instrument process to be detected is not equipped with the DCS system, adopted data memory substitutes the data storage function of the real-time and historical data base of DCS system, and soft measuring instrument is manufactured an independently complete SOC (system on a chip) of the DCS system that do not rely on that comprises I/O element, data-carrier store, program storage, arithmetical unit, several big members of display module, whether be equipped with under the situation of DCS regardless of testing process, can both independently use, more be of value to and promoting the use of.

The polypropylene melting index soft measuring instrument based on blind signal analysis of present embodiment comprises field intelligent instrument 2, fieldbus, data-interface 3, control station 4, the real-time data base 5 that is connected with industrial process object 1, the soft measurement intelligent processor 6 that contains soft measurement function; Process object 1, intelligence instrument 2, DCS system, soft measurement intelligent processor 6 link to each other successively by fieldbus, and the described soft measurement intelligent processor 6 that contains soft measurement function comprises:

Standardization module 7 is used for data are carried out standardization, makes that the average of each variable is 0, and variance is 1, obtains input matrix X, adopts following process to finish, and its formula is (1), (2), (3):

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

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

Wherein, TX is the input sample, and N is a number of training,

Average for training sample;

Blind signal analysis (ICA) module 8 is extracted mutually independently blind source signal from input variable, concrete steps are as follows:

1) choosing norm is 1 initial weight vector (at random) w _i, if i 〉=2, then $w_i=w_i-W_{i-1}{W}_{i-1}^T{w}_i,$ W wherein _I-1=[w ₁w ₂L w _I-1], i=1 ..., m;

2) to w _iCarrying out iteration upgrades: $w_i^{+}=E\left\{\mathrm{xg}\left(w_i^{T}x\right)\right\}-E\{g\text{'}\left(w_i^{T}x\right)\}{w}_i;$

3) standardization $w_i=w_i^{+}/\left|\right|w_i^{+}\left|\right|;$

4) if do not restrain, return 2.Otherwise iteration is to i=m always:

Wherein the condition of convergence is the w of renewal _iWith former w _iDot product is 1, thereby blind source signal can be calculated by S=WX.

Support vector machine modeling (SVM) module 9, concrete steps are as follows:

Find the solution following quadratic programming problem, its formula is (4):

$\underset{{\mathrm{\α},\mathrm{\α}}^{*}}{\max }\{L_D=-\frac{1}{2}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}\underset{j=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})({\mathrm{\α}}_j-{\mathrm{\α}}_j^{*})K(x_i,x_j)-\mathrm{\ϵ}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i+{\mathrm{\α}}_i^{*})+\underset{i=1}{\overset{M}{\mathrm{\Σ}}}{y}_1({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})\}---\left(4\right)$

$s.t.\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})=0$

0≤α _i≤γ

0≤α _i ^*≤γ

Can get w thus and treat estimation function f (x), its formula is (5):

Signal acquisition module 10 is used to set time interval of each sampling, image data from database;

Soft measurement module 11 is used for data to be tested VX the time is obtained with training

And δ _x ²Carry out standardization, and the data after the standardization were advanced after the ICA resume module that obtains of training successively as the input of SVM MBM, the SVM model with input substitution training obtains obtains soft measurement functions value.

Embodiment 2

With reference to Fig. 1, Fig. 2 and Fig. 3, a kind of polypropylene melt index flexible measurement method based on blind signal analysis, described flexible measurement method may further comprise the steps:

(1), determine the key variables that soft measurement is used, from historical data base acquisition system just often the data of described variable as training sample TX;

(2), the extraction blind source signal number of blind signal analysis module, the nuclear parameter of support vector machine MBM and setting sampling period are set;

(3), training sample TX in soft measurement intelligent processor, data are carried out standardization, make that the average of each variable is 0, variance is 1, obtains input matrix X, adopts following process to finish, its formula is (1), (2), (3):

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

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

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

Wherein, TX is a training sample, and N is a number of training,

Average for training sample;

(4), again data are carried out blind signal analysis, concrete steps are:

4.1) to choose norm be 1 initial weight vector (at random) w _i, if i 〉=2, then $w_i=w_i-W_{i-1}{W}_{i-1}^T{w}_i,$ W wherein _I-1=[w ₁w ₂Lw _I-1], i=1 ..., m;

4.2) to w _iCarrying out iteration upgrades: $w_i^{+}=E\left\{\mathrm{xg}\left(w_i^{T}x\right)\right\}-E\{g\text{'}\left(w_i^{T}x\right)\}{w}_i;$

4.3) standardization $w_i=w_i^{+}/\left|\right|w_i^{+}\left|\right|;$

4.4) if do not restrain, return 2.Otherwise iteration is to i=m always;

Wherein the condition of convergence is the w of renewal _iWith former w _iDot product is 1, and blind source signal is calculated by S=WX;

(5), with blind source signal as the input of institute's established model, set up supporting vector machine model, promptly find the solution following quadratic programming problem, its formula is (4):

$\underset{{\mathrm{\α},\mathrm{\α}}^{*}}{\max }\{L_D=-\frac{1}{2}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}\underset{j=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})({\mathrm{\α}}_j-{\mathrm{\α}}_j^{*})K(x_i,x_j)-\mathrm{\ϵ}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i+{\mathrm{\α}}_i^{*})+\underset{i=1}{\overset{M}{\mathrm{\Σ}}}{y}_i({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})\}---\left(4\right)$

$s.t.\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})=0$

0≤α _i≤γ

0≤α _i ^*≤γ

Can get w thus and treat estimation function f (x), its formula is (5):

(6), the data of gathering are sent in the data storage device, from the real-time data base of data storage device, obtain up-to-date variable data at each timing cycle as data VX to be measured; VX the time is obtained with training

And δ _x ²Carry out standardization, and with the input of the data after the standardization as model, the supporting vector machine model with input substitution training obtains obtains soft measurement functions value.

Described flexible measurement method also comprises: (7), regular real data with offline inspection are added in the training set, to upgrade supporting vector machine model.

Described data storage device 5 is the historical data base of DCS system, and described DCS system is made of data-interface 3, control station 4 and historical data base 5, and intelligence instrument 2, DCS system, soft measurement intelligent processor 6 link to each other successively by fieldbus; In described (8), calculate soft measured value, the result is passed to the DCS system, show, and be delivered to operator station by DCS system and fieldbus and show at the control station of DCS.

Claims (7)

1, a kind of polypropylene melting index soft measuring instrument based on blind signal analysis, comprise the field intelligent instrument that is connected with the polypropylene production process object, the data storage device that is used for storing history data and host computer, intelligence instrument, data storage device and host computer link to each other successively, it is characterized in that: described host computer is soft measurement intelligent processor, and described soft measurement intelligent processor comprises:

The standardization module is used for data are carried out standardization, makes that the average of each variable is 0, and variance is 1, obtains input matrix X, adopts following process to finish, and its formula is (1), (2), (3):

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

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

Wherein, TX is a training sample, and N is a number of training, Average for training sample;

The blind signal analysis module is used for according to the blind source signal number of extracting, and extracts mutually independently blind source signal from input variable, and concrete steps are as follows:

1) choosing norm is 1 initial weight vector (at random) w _i, if i 〉=2, then $w_i=w_i-W_{i-1}{W}_{i-1}^T{w}_i,$ W wherein _I-1=[w ₁w ₂L w _1-1], i=1 ..., m;

2) to w _iCarrying out iteration upgrades: $w_i^{+}=E\left\{\mathrm{xg}\right(w_i^{T}x\left)\right\}-E\left\{g^{\text{'}}\right(w_i^{T}x\left)\right\}{w}_i,$ W wherein _i ⁺Weight vectors after expression is upgraded, E is a mathematical expectation, g (u)=uexp (u ²/ 2);

3) standardization $w_i=w_i^{+}/\left|\right|w_i^{+}\left|\right|,$ ‖ w wherein _i ⁺‖ represents w _i ⁺Norm;

4) if do not restrain, return 2, otherwise always iteration to i=m;

Wherein the condition of convergence is the w of renewal _iWith former w _iDot product is 1, thereby blind source signal can be calculated by S=WX;

The support vector machine MBM is used for according to the support vector machine nuclear parameter, calculates kernel function, and concrete steps are as follows:

Find the solution following quadratic programming problem, its formula is (4):

$\underset{{\mathrm{\α},\mathrm{\α}}^{*}}{\max }\{L_D=-\frac{1}{2}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}\underset{j=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})({\mathrm{\α}}_j-{\mathrm{\α}}_j^{*})K(x_i,x_j)-\mathrm{\ϵ}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i+{\mathrm{\α}}_i^{*})+\underset{i=1}{\overset{M}{\mathrm{\Σ}}}{y}_i({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})\}---\left(4\right)$

$s.t.\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})=0$

0≤α _i≤γ

$0\≤{\mathrm{\α}}_i^{*}\≤\mathrm{\γ}$

Calculate w thus and treat estimation function f (x), its formula is (5):

Wherein, α _i(i=1 ..., N) be the Lagrange multiplier, x _i(i=1 ..., N) be input vector, y is an output variable, ω is the normal vector of support vector machine lineoid, the direction of decision lineoid, the position of b decision lineoid;

Signal acquisition module is used to set time interval of each sampling, image data from database; Soft measurement module is used for data to be tested VX the time is obtained with training

And δ _x ²Carry out standardization, and with the data after the standardization through the blind signal analysis resume module that obtains of training after as the input of support vector machine MBM, the supporting vector machine model with input substitution training obtains obtains soft measurement functions value.

2, the polypropylene melting index soft measuring instrument based on blind signal analysis as claimed in claim 1, it is characterized in that: described soft measurement intelligent processor also comprises: the model modification module, be used for regular real data and be added to training set, upgrade supporting vector machine model offline inspection.

3, the polypropylene melting index soft measuring instrument based on blind signal analysis as claimed in claim 1 or 2, it is characterized in that: described soft measuring instrument also comprises the DCS system, described DCS system is made of data-interface, control station and historical data base, described data storage device is the historical data base of DCS system, described soft measurement intelligent processor also comprises: display module as a result is used for soft measurement result.

4, the polypropylene melting index soft measuring instrument based on blind signal analysis as claimed in claim 3, it is characterized in that: described field intelligent instrument, DCS system, soft measurement intelligent processor connect successively by fieldbus.

5, a kind of usefulness flexible measurement method of realizing based on the polypropylene melting index soft measuring instrument of blind signal analysis as claimed in claim 1, it is characterized in that: described flexible measurement method may further comprise the steps:

(1), determine the key variables that soft measurement is used, from historical data base acquisition system just often the data of described variable as training sample TX;

(2), the extraction blind source signal number of blind signal analysis module, the nuclear parameter of support vector machine MBM and setting sampling period are set;

(3), training sample TX in soft measurement intelligent processor, data are carried out standardization, make that the average of each variable is 0, variance is 1, obtains input matrix X, adopts following process to finish, its formula is (1), (2), (3):

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

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

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

Wherein, TX is a training sample, and N is a number of training,

Average for training sample;

(4), again data are carried out blind signal analysis, concrete steps are:

4.1) to choose norm be 1 initial weight vector (at random) w _i, if i 〉=2, then $w_i=w_i-W_{i-1}{W}_{i-1}^T{w}_i,$ W wherein _I-1=[w ₁w ₂L w _I-1], i=1 ..., m;

4.2) to w _iCarrying out iteration upgrades: $w_i^{+}=E\left\{\mathrm{xg}\left(w_i^{T}x\right)\right\}-E\left\{g^{\text{'}}\left(w_i^{T}w\right)\right\}{w}_i;$

4.3) standardization $w_i=w_i^{+}/\left|\right|w_i^{+}\left|\right|;$

4.4) if do not restrain, return 2.Otherwise iteration is to i=m always;

Wherein the condition of convergence is the w of renewal _iWith former w _iDot product is 1, and blind source signal is calculated by S=WX;

(5), with blind source signal as the input of institute's established model, set up supporting vector machine model, promptly find the solution following quadratic programming problem, its formula is (4):

$\underset{{\mathrm{\α},\mathrm{\α}}^{*}}{\max }\{L_D=-\frac{1}{2}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}\underset{j=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})({\mathrm{\α}}_j-{\mathrm{\α}}_j^{*})K(x_i,x_j)-\mathrm{\ϵ}\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i+{\mathrm{\α}}_i^{*})+\underset{i=1}{\overset{M}{\mathrm{\Σ}}}{y}_i({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})\}---\left(4\right)$

$s$ $.$ $t.\underset{i=1}{\overset{M}{\mathrm{\Σ}}}({\mathrm{\α}}_i-{\mathrm{\α}}_i^{*})$ $=0$

0≤α _i≤γ

$0\≤{\mathrm{\α}}_i^{*}\≤\mathrm{\γ}$

Can get w thus and treat estimation function f (x), its formula is (5):

(6), the data of gathering are sent in the data storage device, from the real-time data base of data storage device, obtain up-to-date variable data at each timing cycle as data VX to be measured; VX the time is obtained with training And δ _x ²Carry out standardization, and with the input of the data after the standardization as model, the supporting vector machine model with input substitution training obtains obtains soft measurement functions value.

6, the polypropylene melt index flexible measurement method based on blind signal analysis as claimed in claim 5, it is characterized in that: described flexible measurement method also comprises: (7), regular real data with offline inspection are added in the training set, to upgrade supporting vector machine model.

7, as claim 5 or 6 described polypropylene melt index flexible measurement methods based on blind signal analysis, it is characterized in that: described data storage device is the historical data base of DCS system, and described DCS system is made of data-interface, control station and historical data base; In described (6), calculate soft measured value, the result is passed to the DCS system, show, and be delivered to operator station by DCS system and fieldbus and show at the control station of DCS.

Images