CN100470427C - Industrial soft measuring instrument based on bionic intelligence and soft measuring method therefor - Google Patents

Abstract

A soft measuring meter based on bionic intelligence comprises on site intelligent meter connected with the industrial process object, storage device and upper position machine, intelligent meter, data storage device and the upper position machine connected sequentially, the said upper position machine being soft measurement intelligent processor, which comprises standardized handling module, radial basic function neural network establishment module, module parameter optimization module based on chaotic genetic algorithm, signal sampling module and soft measurement module. It also puts forward a failure diagnostic method. It is convenient, extensive in application, fine in measuring result, high in precision.

Description

Industrial soft measuring instrument and flexible measurement method based on bionic intelligence

(1) technical field

The present invention relates to the soft fields of measurement of industrial process, especially, relate to a kind of industrial soft measuring instrument and flexible measurement method based on bionic intelligence.

(2) background technology

In modern process industry, parameters such as a large amount of key process statuses, product quality lack online direct measurement means.This has become the bottleneck that restriction production safety, product quality, output and productivity effect further improve.Soft-measuring technique formally solves the effective way of this type of problem.

Utilize industrial measured data, adopt the method for adding up to set up the soft-sensing model of industrial process, avoided complicated Analysis on Mechanism, model is to the degree that the fits height of observation data, and it is convenient relatively to find the solution, and is a kind of effective means and the instrument that carries out soft measurement.

But common most of soft measuring instruments and method often exist the instrument parameter to determine problems such as difficult, poor for applicability and soft instrument precision is not high, are difficult to be suitable at the soft measurement industrial process of high precision.

(3) summary of the invention

Determine the deficiency difficult, poor for applicability, that precision is not high for the parameter that overcomes existing industrial soft measuring instrument, the invention provides industrial soft measuring system and flexible measurement method that a kind of parameter determines that convenient, applied widely, soft measurement effect is good, precision is high based on bionic intelligence.

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

A kind of industrial soft measuring instrument based on bionic intelligence, comprise the field intelligent instrument that is connected with industrial 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, and TX is the average of training sample;

The radial basis function neural network MBM is used to set up soft-sensing model RBF, adopts following process:

1) selects Gaussian function Φ (υ)=exp (υ for use ²/ α ²) as the activation function of network, given form parameter α;

2) determine RBF center vector C with the least square learning algorithm _i

3) orthogonal optimum seeking determines that best hidden layer number, network output weights obtain soft-sensing model, and its formula is (4):

$f\left(X\right)={\mathrm{\ω}}_0+\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{\mathrm{\ω}}_i\mathrm{\Φ}\left(\left|\right|X-C_i\left|\right|\right)---\left(4\right)$

Wherein, X ∈ R ⁿIt is input vector; Φ () is from R ⁺The nonlinear function of → R; C _i∈ R ⁿ(1≤i≤N) is the RBF center; ω _i(1≤i≤N) for connecting weights, ω ₀Be amount of bias; N is the neuron number of hidden layer; ‖ ‖ is the Euclidean norm;

Model parameter preferred module based on Chaos Genetic Algorithm is used to optimize the RBF model parameter, adopts following process:

1) treats parameters optimization, be designated as x, carry out binary coding, generate initial population, calculate each individual fitness value;

2) (fi (fi is an individual fitness) population scale in accordance with regulations selects individuality to enter the next generation according to selecting Probability p i=fi/ ∑ ifi;

3) with crossover probability by suitable interleaved mode to many individuality being intersected of choosing;

4) with variation Probability p m by the suitable individual variation of variation mode to choosing;

5) each individual fitness value is calculated in decoding;

6) determine the fitness intermediate value, the individuality that adaptive value is bigger than intermediate value is not done chaotic disturbance, the individuality that remaining adaptive value is littler than intermediate value is done chaotic disturbance, the amplitude controlled variable of chaotic disturbance increases along with iterations and diminishes; Calculate new individual fitness value; Chaotic disturbance carries out as follows:

Select the Logistic mapping for use, its formula is (5):

x _n+1＝4·x _n(1-x _n) (5)

The Chaos Variable that obtains according to following formula (5) by transformed mappings to the variable that will optimize, transformation for mula following (6):

x _i＝c _i+d _ix _i (6)

7) repeating step 2 is satisfied up to end condition to step 6, and the fitness value of the new individuality that promptly calculates remained unchanged within 5 generations;

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

Carry out standardization, and with the input of the data after the standardization as the radial basis function neural network MBM, the RBF 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 is used for regularly the real data of offline inspection is added to training set, to upgrade the RBF 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 industrial soft measuring instrument of bionic intelligence 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), in model parameter preferred module based on Chaos Genetic Algorithm, the population size of Chaos Genetic Algorithm, maximum algebraically are set, select probability, crossover probability, variation probability parameter, and set the sampling period among the DCS;

(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, and TX is the average of training sample;

(4), set up radial primary function network, concrete steps are:

4.1) select Gaussian function Φ (υ)=exp (υ for use ²/ α ²) as the activation function of network, given form parameter α;

4.2) determine RBF center vector C with the least square learning algorithm _i

4.3) orthogonal optimum seeking determines that best hidden layer number, network output weights obtain soft-sensing model, its formula is (4):

$f\left(X\right)={\mathrm{\ω}}_0+\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{\mathrm{\ω}}_i\mathrm{\Φ}\left(\left|\right|X-C_i\left|\right|\right)---\left(4\right)$

Wherein, X ∈ R ⁿIt is input vector; Φ () is from R ⁺The nonlinear function of → R; C _i∈ R ⁿ(1≤i≤N) is the RBF center; ω _i(1≤i≤N) for connecting weights, ω ₀Be amount of bias; N is the neuron number of hidden layer; ‖ ‖ is the Euclidean norm;

(5), optimize above-mentioned parameter α, concrete steps are with Chaos Genetic Algorithm:

5.1) treat parameters optimization and carry out binary coding, generate initial population, calculate each individual fitness value;

5.2) (fi (fi is an individual fitness) population scale in accordance with regulations selects individuality to enter the next generation according to selecting Probability p i=fi/ ∑ ifi;

5.3) with crossover probability by suitable interleaved mode to many individuality being intersected of choosing;

5.4) with variation Probability p m by the suitable individual variation of variation mode to choosing;

5.5) decoding, calculate each individual fitness value;

5.6) determine the fitness intermediate value, the individuality that adaptive value is bigger than intermediate value is not done chaotic disturbance, the individuality that remaining adaptive value is littler than intermediate value is done chaotic disturbance, the amplitude controlled variable of chaotic disturbance increases along with iterations and diminishes; Calculate new individual fitness value; Chaotic disturbance carries out as follows:

Select the Logistic mapping for use, its formula is (5):

α _n+1＝4·α _n(1-α _n) (5)

The Chaos Variable that obtains according to following formula by transformed mappings to the variable that will optimize, transformation for mula following (6):

α _i＝c _i+d _iα _i (6)

5.7) repeat 5.2 to 5.6, satisfied up to end condition, the fitness value of the new individuality that promptly calculates remained unchanged within 5 generations;

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

Carry out standardization, and with the input of the data after the standardization as the radial basis function neural network MBM, the RBF 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 the radial basis function neural network 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: bionic intelligence such as genetic algorithm etc., can simulate the parameter of the intelligent evolutionary process of biological evolution and biotic population according to the characteristics optimization soft measuring instrument of testing process, determine problems such as difficult, poor for applicability and soft instrument precision is not high thereby effectively solve conventional soft instrument parameter, in difficulties such as the soft measurement industrial process of high precision are difficult to be suitable for.

Industrial process data itself has very severe nonlinear, and RBF can well approach this nonlinear relationship; Chaos Genetic Algorithm had both kept the ability of searching optimum of genetic algorithm, can obviously improve the speed of convergence of genetic algorithm again, can within a short period of time the Optimization Model parameter.

Beneficial effect of the present invention mainly shows: 1, applied widely, can extensively apply to various industrial processs; 2, soft measurement effect is good; 3, operation efficiency height, model can online updating; 4, use simply, in existing DCS system, realize easily, also can constitute an independently system.

(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;

(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, a kind of industrial soft measuring instrument based on bionic intelligence, comprise the field intelligent instrument 2 that is connected with industrial process object 1, the data storage device 5 that is used for storing history data and host computer 5, intelligence instrument 2, data storage device 5 and host computer 6 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, and TX is the average of training sample;

Radial basis function neural network MBM (RBF module) 8 is used to set up soft-sensing model RBF, adopts following process:

1) selects Gaussian function Φ (υ)=exp (υ for use ²/ α ²) as the activation function of network, given form parameter α;

2) determine RBF center vector C with the least square learning algorithm _i

3) orthogonal optimum seeking determines that best hidden layer number, network output weights obtain soft-sensing model, and its formula is (4):

$f\left(X\right)={\mathrm{\ω}}_0+\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{\mathrm{\ω}}_i\mathrm{\Φ}\left(\left|\right|X-C_i\left|\right|\right)---\left(4\right)$

Wherein, X ∈ R ⁿIt is input vector; Φ () is from R ⁺The nonlinear function of → R; C _i∈ R ⁿ(1≤i≤N) is the RBF center; ω _i(1≤i≤N) for connecting weights, ω ₀Be amount of bias; N is the neuron number of hidden layer; ‖ ‖ is the Euclidean norm;

Model parameter preferred module (CGA) 9 based on Chaos Genetic Algorithm is used to optimize the RBF model parameter, adopts following process:

1) treats parameters optimization, be designated as x, carry out binary coding, generate initial population, calculate each individual fitness value;

2) (fi (fi is an individual fitness) population scale in accordance with regulations selects individuality to enter the next generation according to selecting Probability p i=fi/ ∑ ifi;

3) with crossover probability by suitable interleaved mode to many individuality being intersected of choosing;

4) with variation Probability p m by the suitable individual variation of variation mode to choosing;

5) each individual fitness value is calculated in decoding;

6) determine the fitness intermediate value, the individuality that adaptive value is bigger than intermediate value is not done chaotic disturbance, the individuality that remaining adaptive value is littler than intermediate value is done chaotic disturbance, the amplitude controlled variable of chaotic disturbance increases along with iterations and diminishes; Calculate new individual fitness value; Chaotic disturbance carries out as follows:

Select the Logistic mapping for use, its formula is (5):

x _n+1＝4·x _n(1-x _n) (5)

The Chaos Variable that obtains according to following formula (5) by transformed mappings to the variable that will optimize, transformation for mula following (6):

x _i＝c _i+d _ix _i (6)

7) repeating step 2 is satisfied up to end condition to step 6, and the fitness value of the new individuality that promptly calculates remained unchanged within 5 generations;

Signal acquisition module 10 is used for the time interval according to each sampling of setting, image data from database;

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

Carry out standardization, and the data after the standardization were advanced the offset minimum binary module that obtains of training successively and the multiresolution decomposing module is handled the input of back as the radial basis function neural network MBM, radial basis function neural network model with input substitution training obtains obtains soft measurement functions value through the multiresolution reconstructed module again.

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 the radial basis function neural network 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 industrial soft measuring instrument based on bionic intelligence of present embodiment comprises the field intelligent instrument 2, DCS system and the intelligent element 6 that are connected with industrial process object 1, and described DCS system is made of data-interface 3, control station 4, database 5; Intelligence instrument 2, DCS system, soft measurement intelligent processor 6 link to each other successively by fieldbus, and described soft measurement intelligent processor 6 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: ${\mathrm{\σ}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}({\mathrm{TX}}_i-\stackrel{\‾}{\mathrm{TX}}),---\left(2\right)$

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

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

Radial basis function neural network MBM 8 is used to set up soft-sensing model, adopts following process:

1) selects Gaussian function Φ (υ)=exp (υ for use ²/ α ²) as the activation function of network, given form parameter α;

2) determine RBF center vector C with the least square learning algorithm _i

3) orthogonal optimum seeking determines that best hidden layer number, network output weights obtain soft-sensing model, and its formula is (4):

$f\left(X\right)={\mathrm{\ω}}_0+\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{\mathrm{\ω}}_i\mathrm{\Φ}\left(\left|\right|X-C_i\left|\right|\right)---\left(4\right)$

Wherein, X ∈ R ⁿIt is input vector; Φ () is from R ⁺The nonlinear function of → R; C _i∈ R ⁿ(1≤i≤N) is the RBF center; ω _i(1≤i≤N) for connecting weights, ω ₀Be amount of bias; N is the neuron number of hidden layer; ‖ ‖ is the Euclidean norm;

Model parameter preferred module 9 based on Chaos Genetic Algorithm is used for optimizing the RBF model parameter, promotes the modeling effect, adopts following process:

1) treats parameters optimization (being designated as x) and carry out binary coding, generate initial population, calculate each individual fitness value;

2) (fi (fi is an individual fitness) population scale in accordance with regulations selects individuality to enter the next generation according to selecting Probability p i=fi/ ∑ ifi;

3) with crossover probability by suitable interleaved mode to many individuality being intersected of choosing;

4) with variation Probability p m by the suitable individual variation of variation mode to choosing, show through Computer Simulation: if algorithm iteration number of times few (in 50 times) has had chaotic disturbance, this step can be omitted, thereby can save a large amount of time;

5) each individual fitness value is calculated in decoding;

6) the bigger individuality of adaptive value is not done chaotic disturbance, only remaining adaptive value small individuals is done chaotic disturbance, the amplitude controlled variable of chaotic disturbance increases along with iterations and diminishes.Calculate new individual fitness value.Chaotic disturbance carries out as follows:

Select the Logistic mapping for use, its formula is (5):

x _n+1＝4·x _n(1-x _n) (5)

The Chaos Variable that obtains according to following formula by transformed mappings to the variable that will optimize, in order to avoid at unnecessary space search, transformation for mula following (6):

x _i＝c _i+d _ix _i (6)

7) repeating step 2 is satisfied up to end condition to step 6, and the fitness value of the new individuality that promptly calculates remained unchanged within 5 generations;

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

Soft measurement module 11, be used for TX that data to be tested VX the time is obtained with training and Carry out standardization, and with the input of the data after the standardization as the RBF MBM, the RBF 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 the RBF model.Display module 13 as a result, are used for soft measurement result is passed to the DCS system, show at the control station of DCS, and are delivered to operator station by DCS system and fieldbus and show.

Embodiment 2

With reference to Fig. 1, Fig. 2, a kind of industrial soft measurement method based on bionic intelligence, 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), in model parameter preferred module based on Chaos Genetic Algorithm, the population size of Chaos Genetic Algorithm, maximum algebraically are set, select probability, crossover probability, variation probability parameter, and set the sampling period;

(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, the average of TX training sample;

(4), set up radial primary function network, concrete steps are:

4.1) select Gaussian function Φ (υ)=exp (υ for use ²/ α ²) as the activation function of network, given form parameter α:

4.2) determine RBF center vector C with the least square learning algorithm _i

4.3) orthogonal optimum seeking determines that best hidden layer number, network output weights obtain soft-sensing model, its formula is (4):

$f\left(X\right)={\mathrm{\ω}}_0+\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{\mathrm{\ω}}_i\mathrm{\Φ}\left(\left|\right|X-C_i\left|\right|\right)---\left(4\right)$

Wherein, X ∈ R ⁿIt is input vector; Φ () is from R ⁺The nonlinear function of → R; C _i∈ R ⁿ(1≤i≤N) is the RBF center; ω _i(1≤i≤N) for connecting weights, ω ₀Be amount of bias; N is the neuron number of hidden layer; ‖ ‖ is the Euclidean norm;

(5), optimize above-mentioned parameter α, concrete steps are with Chaos Genetic Algorithm:

5.1) treat parameters optimization and carry out binary coding, generate initial population, calculate each individual fitness value;

5.2) (fi (fi is an individual fitness) population scale in accordance with regulations selects individuality to enter the next generation according to selecting Probability p i=fi/ ∑ ifi;

5.3) with crossover probability by suitable interleaved mode to many individuality being intersected of choosing;

5.4) with variation Probability p m by the suitable individual variation of variation mode to choosing;

5.5) decoding, calculate each individual fitness value;

5.6) determine the fitness intermediate value, the individuality that adaptive value is bigger than intermediate value is not done chaotic disturbance, the individuality that remaining adaptive value is littler than intermediate value is done chaotic disturbance, the amplitude controlled variable of chaotic disturbance increases along with iterations and diminishes; Calculate new individual fitness value; Chaotic disturbance carries out as follows:

Select the Logistic mapping for use, its formula is (5):

α _n+1＝4·α _n(1-α _n) (5)

The Chaos Variable that obtains according to following formula by transformed mappings to the variable that will optimize, transformation for mula following (6):

α _i＝c _i+d _iα _i (6)

5.7) repeat 5.2 to 5.6, satisfied up to end condition, the fitness value of the new individuality that promptly calculates remained unchanged within 5 generations;

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

Carry out standardization, and with the input of the data after the standardization as the radial basis function neural network MBM, the RBF 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 the radial basis function neural network 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 industrial soft measuring instrument based on bionic intelligence, comprise the field intelligent instrument that is connected with industrial 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: ${\mathrm{\σ}}_x^2=\frac{1}{N-1}\underset{i=1}{\overset{N}{\mathrm{\Σ}}}({\mathrm{TX}}_i-\stackrel{\‾}{\mathrm{TX}})---\left(2\right)$

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

Wherein, TX is a training sample, N _TrainN is a number of training, and TX is the average of training sample;

The radial basis function neural network MBM is used to set up soft-sensing model RBF, adopts following process:

1) select for use Gaussian function Φ (v)=exp (v ²/ α ²) as the activation function of network, given form parameter α;

2) determine RBF center vector C with the least square learning algorithm _i

3) orthogonal optimum seeking determines that best hidden layer number, network output weights obtain soft-sensing model, and its formula is (4):

$f\left(X\right)={\mathrm{\ω}}_0+\underset{i=1}{\overset{N}{\mathrm{\Σ}}}{\mathrm{\ω}}_i\mathrm{\Φ}\left(\left|\right|X-C_i\left|\right|\right)---\left(4\right)$

Wherein, X ∈ R ⁿIt is input vector; Φ () is from R ⁺The nonlinear function of → R; C _i∈ R ⁿ(1≤i≤n) is the RBF center; ω _i(1≤i≤n) for connecting weights, ω ₀Be amount of bias; N is the neuron number of hidden layer; ‖ ‖ is the Euclidean norm;

Model parameter preferred module based on Chaos Genetic Algorithm is used to optimize the RBF model parameter, adopts following process:

1) treats parameters optimization, be designated as x, carry out binary coding, generate initial population, calculate each individual fitness value;

2) according to selecting Probability p i=fi/ ∑ ifi, (wherein, fi is an individual fitness, and population scale in accordance with regulations selects individuality to enter the next generation;

3) with crossover probability by suitable interleaved mode to many individuality being intersected of choosing;

4) with variation Probability p m by the suitable individual variation of variation mode to choosing;

5) each individual fitness value is calculated in decoding;

6) determine the fitness intermediate value, the individuality that adaptive value is bigger than intermediate value is not done chaotic disturbance, the individuality that remaining adaptive value is littler than intermediate value is done chaotic disturbance, the amplitude controlled variable of chaotic disturbance increases along with iterations and diminishes; Calculate new individual fitness value; Chaotic disturbance carries out as follows:

Select the Logistic mapping for use, its formula is (5):

x _n+1＝4·x _n(1-x _n) (5)

The Chaos Variable that obtains according to following formula (5) by transformed mappings to the variable that will optimize, transformation for mula following (6):

x _i＝c _i+d _ix _i (6)

7) repeating step 2 is satisfied up to end condition to step 6, and the fitness value of the new individuality that promptly calculates remained unchanged within 5 generations;

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

Soft measurement module, be used for TX that data to be tested VX the time is obtained with training and

Carry out standardization, and with the input of the data after the standardization as the radial basis function neural network MBM, the RBF model with input substitution training obtains obtains soft measurement functions value.

2, the industrial soft measuring instrument based on bionic intelligence 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, to upgrade the RBF model offline inspection.

3, the industrial soft measuring instrument based on bionic intelligence 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, and 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, and show at the control station of DCS, and be delivered to operator station by DCS system and fieldbus and show.

4, the industrial soft measuring instrument based on bionic intelligence as claimed in claim 3 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 industrial soft measuring instrument of bionic intelligence as claimed in claim 1 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), in model parameter preferred module based on Chaos Genetic Algorithm, the population size of Chaos Genetic Algorithm, maximum algebraically are set, select probability, crossover probability, variation probability parameter, and set the sampling period;

(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, and TX is the average of training sample;

(4), set up radial primary function network, concrete steps are:

4.1) select for use Gaussian function Φ (v)=exp (v ²/ α ²) as the activation function of network, given form parameter α;

4.2) determine RBF center vector C with the least square learning algorithm _i

4.3) orthogonal optimum seeking determines that best hidden layer number, network output weights obtain soft-sensing model, its formula is (4):

$f\left(X\right)={\mathrm{\ω}}_0+\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{\mathrm{\ω}}_i\mathrm{\Φ}\left(\left|\right|X-C_i\left|\right|\right)---\left(4\right)$

Wherein, X ∈ R ⁿIt is input vector; Φ () is from R ⁺The nonlinear function of → R; C _i∈ R ⁿ(1≤i≤n) is the RBF center; ω _i(1≤i≤n) for connecting weights, ω ₀Be amount of bias; N is the neuron number of hidden layer; ‖ ‖ is the Euclidean norm;

(5), optimize above-mentioned parameter α, concrete steps are with Chaos Genetic Algorithm:

5.1) treat parameters optimization and carry out binary coding, generate initial population, calculate each individual fitness value;

5.2) according to selecting Probability p i=fi/ ∑ ifi wherein, fi is an individual fitness, population scale in accordance with regulations selects individuality to enter the next generation;

5.3) with crossover probability by suitable interleaved mode to many individuality being intersected of choosing;

5.4) with variation Probability p m by the suitable individual variation of variation mode to choosing;

5.5) decoding, calculate each individual fitness value;

5.6) determine the fitness intermediate value, the individuality that adaptive value is bigger than intermediate value is not done chaotic disturbance, the individuality that remaining adaptive value is littler than intermediate value is done chaotic disturbance, the amplitude controlled variable of chaotic disturbance increases along with iterations and diminishes; Calculate new individual fitness value; Chaotic disturbance carries out as follows:

Select the Logistic mapping for use, its formula is (5):

α _n+1＝4·α _n(1-α _n) (5)

The Chaos Variable that obtains according to following formula by transformed mappings to the variable that will optimize, transformation for mula following (6):

α _i＝c _i+d _iα _i (6)

5.7) repeat 5.2 to 5.6, satisfied up to end condition, the fitness value of the new individuality that promptly calculates remained unchanged within 5 generations;

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

Carry out standardization, and with the input of the data after the standardization as the radial basis function neural network MBM, the RBF model with input substitution training obtains obtains soft measurement functions value.

6, flexible measurement method as claimed in claim 5 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 the radial basis function neural network model.

7, as claim 5 or 6 described flexible measurement methods, 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