CN109726474A - A kind of multiple dimensioned forecast system of the propylene polymerization production process of on-line correction - Google Patents
A kind of multiple dimensioned forecast system of the propylene polymerization production process of on-line correction Download PDFInfo
- Publication number
- CN109726474A CN109726474A CN201811625146.XA CN201811625146A CN109726474A CN 109726474 A CN109726474 A CN 109726474A CN 201811625146 A CN201811625146 A CN 201811625146A CN 109726474 A CN109726474 A CN 109726474A
- Authority
- CN
- China
- Prior art keywords
- scale
- data
- production process
- propylene polymerization
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012937 correction Methods 0.000 title claims abstract description 42
- QQONPFPTGQHPMA-UHFFFAOYSA-N propylene Natural products CC=C QQONPFPTGQHPMA-UHFFFAOYSA-N 0.000 title claims abstract description 42
- 125000004805 propylene group Chemical group [H]C([H])([H])C([H])([*:1])C([H])([H])[*:2] 0.000 title claims abstract description 42
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 35
- 238000006116 polymerization reaction Methods 0.000 title claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000005259 measurement Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 239000000155 melt Substances 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 230000009977 dual effect Effects 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005293 physical law Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000036962 time dependent Effects 0.000 claims description 3
- -1 Polypropylene Polymers 0.000 description 11
- 239000004743 Polypropylene Substances 0.000 description 10
- 229920001155 polypropylene Polymers 0.000 description 10
- FFBHFFJDDLITSX-UHFFFAOYSA-N benzyl N-[2-hydroxy-4-(3-oxomorpholin-4-yl)phenyl]carbamate Chemical compound OC1=C(NC(=O)OCC2=CC=CC=C2)C=CC(=C1)N1CCOCC1=O FFBHFFJDDLITSX-UHFFFAOYSA-N 0.000 description 4
- 239000003054 catalyst Substances 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 2
- 238000007334 copolymerization reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 239000001257 hydrogen Substances 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 229920005992 thermoplastic resin Polymers 0.000 description 2
- 239000004698 Polyethylene Substances 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011127 biaxially oriented polypropylene Substances 0.000 description 1
- 229920006378 biaxially oriented polypropylene Polymers 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004745 nonwoven fabric Substances 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 229920000915 polyvinyl chloride Polymers 0.000 description 1
- 239000004800 polyvinyl chloride Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of multiple dimensioned forecast systems of the propylene polymerization production process of on-line correction, for carrying out melt index forecast, including data preprocessing module, multiscale analysis module, forecasting model module and on-line correction module to propylene polymerization production process.The present invention forecasts the important parameter index melt index of propylene polymerization production process, overcome the shortcomings of that current existing forecast system measurement accuracy is not high, anti-interference ability is weak, introduce the technological means of on-line correction and multiscale analysis, to obtain the multiple dimensioned forecast system of propylene polymerization production process of on-line correction, the propylene polymerization production process melt index forecast system of realization can make full use of the creation data of production of propylene process, the online correction for completing forecasting model parameter, have high forecast precision and anti-interference ability.
Description
Technical Field
The invention relates to an online forecasting system, in particular to an online-corrected multi-scale forecasting system in a propylene polymerization production process.
Background
Polypropylene is a thermoplastic resin, is produced by propylene polymerization, is one of five general-purpose plastics, and is closely related to our daily life. Polypropylene is the most important downstream product of propylene, and 50 percent of the total propylene yield in the world and 65 percent of the propylene yield in China are used for producing the polypropylene. Polypropylene is the fastest growing commodity thermoplastic resin worldwide, second only to polyethylene and polyvinyl chloride. In order to make the polypropylene products in China have market competitiveness, the development of impact-resistant copolymerization products, random copolymerization products, BOPP and CPP film materials, fibers and non-woven fabrics with good balance of rigidity, toughness and fluidity and the application of polypropylene in the fields of automobiles and household appliances are important research subjects in the future.
The melt index is one of the important quality indexes of polypropylene products for determining the grade of the products, and determines different purposes of the products. The measurement of the melt index is an important link of product quality control in polypropylene production, and has very important function and guiding significance for production and scientific research.
However, the online analysis and measurement of the melt index are difficult to achieve at present, on one hand, the lack of the online melt index analyzer is caused, and on the other hand, the existing online analyzer is difficult to use due to the fact that the online melt index analyzer is often blocked and inaccurate in measurement or even cannot be used normally. Therefore, currently, MI measurement in industrial production is mainly obtained by manual sampling and off-line assay analysis, and generally, MI can only be analyzed once every 2-4 hours, so that the time delay is large, which brings difficulty to quality control of propylene polymerization production and becomes a bottleneck problem to be solved urgently in production. The online forecasting system research of the polypropylene melt index becomes a leading edge and a hot spot of academia and industry.
Disclosure of Invention
In order to overcome the defects of low prediction precision and weak anti-interference capability of the existing propylene polymerization production process prediction system, the invention aims to provide the online correction propylene polymerization production process multi-scale prediction system, which can fully utilize data multi-scale information and realize automatic online correction of a model, and has high prediction precision and strong anti-interference capability.
The purpose of the invention is realized by the following technical scheme: an online-corrected multi-scale forecasting system for a propylene polymerization production process is used for forecasting a melt index in the propylene polymerization production process and comprises a data preprocessing module, a multi-scale analysis module, a forecasting model module and an online correction module.
Further, the input of the data preprocessing module is 9 variables of the propylene polymerization production processSince each variable has different units, in order to prevent different dimensions from causing errors between data magnitudes, all data are normalized, and the normalization formula is as follows:
wherein mean is the arithmetic mean of each variable, std is the standard deviation of each variable,the subscript r is the value of the input variable, r is the detection of the r, s is the variable of the s dimension, xrsAs the value of the normalized input variableAnd inputting data. Normalized data is S ═ xr1,xr2,...,xr9}。
Furthermore, the multi-scale analysis module simultaneously observes the frequency and the time axis of the input data through multi-scale analysis, and has better time resolution when the frequency is high and better frequency resolution when the frequency is low so as to acquire data information under multi-scale. Normalizing the data S to { x ═ xr1,xr2,...xr9Performing multi-scale analysis as follows:
(1) representing the corresponding input data at the current scale J as SJAccording to the following formula to SJWavelet decomposition is performed, and the dimension J is reduced by 1:
wherein, J0In order to be the initial scale, the method comprises the following steps,is the coefficient sequence basis function and psi is the difference sequence basis function.Is scale J0The next k-th coefficient sequence basis function,is prepared by reacting withCorresponding weight coefficient,. psil,kIs the k-th difference sequence basis function at the scale l, dl,kIs equal to psil,kThe corresponding weight coefficients.
Wherein j is the jth scale,for the k-th coefficient sequence basis function at the scale j,is equal to time 2jAnd the t-k related coefficient sequence constant takes the following values:
wherein, t is the time,is a constant related to t. And defines:
wherein psi0,0(t) is a time-dependent constant,is equal to the dimension J0-1 k-th difference sequence basis functionThe corresponding weight coefficients. Thereby obtaining:
wherein d isj,kIs the k-th difference sequence basis function psi under the scale jj,kThe corresponding weight coefficients. When J is 1, stopping decomposition and obtaining a series of corresponding wavelet analysis coefficients d under the current scale J(l)＝{d1,d2,…dJ-1}。
(2) Updating the time segment T in the current iteration by interpolation(l)If its corresponding wavelet analysis coefficientThe following conditions are met:
the corresponding time segments are combined, where eeGiven a normal number.
(3) If its corresponding wavelet analysis coefficientThe following conditions are met:
further interpolation is performed on the corresponding time segment; so as to obtain a new optimized running time segment T(l +1)In which epsiloniGiven a normal number.
Further, the forecasting model module uses a statistical modeling method to complete the highly nonlinear mapping from the input parameters to the output melt index forecasting values by minimizing an error function, and the topological invariance is kept in the mapping:
where Γ represents an objective function, w represents inertial weights, ξ represents errors, C represents penalty factors, u represents weight coefficients, β represents kernel function mapping, b represents bias, x is input data, y is output data, subscript i represents ith data, n is the total number of output variables, and superscript T represents the transpose of the matrix.
Further, the online correction module adopts an online correction strategy to correct the parameters of the prediction model module in real time, and corrects the model error in real time by adding the prediction data with larger prediction error into the training data set as new training data: (1) the online correction module obtains the correction value of the measurement data, so that the correction value meets the material and energy balance relation of the whole device and unit equipment, and the weighted square sum of the difference between the correction value and the measurement value is minimum.
MIp＝MIa+ε (12)
Wherein MI is melt index, MIpFor melt index measurements, MIaIs the true value of the melt index, epsilon is the error vector,for the correction values, U is the prediction model parameter vector,and F is a prediction model function vector which represents chemical and physical laws such as material balance, energy balance, chemical reaction metering relation and the like in the propylene polymerization process. The (n × n) order variance-covariance matrix, where Q is MI, can be estimated from the meter accuracy or measurement samples.
(2) When the on-line correction module works, the analysis value MI at the moment t is obtained in real timea(t) and the predicted value MIp(t)，Calculating an analytical value MIaAnd predicted value MIpDeviation e ofo(t)：
eo(t)＝|MIa(t)－MIp(t)| (14)
If eo(t) greater than a positive error margin εo：
eo(t)＞εo(15)
The analysis value MI at the time point t is compareda(t) and parameter values x (t) as new training data { x (t), MIaAnd (t) adding the training data set, retraining the parameters of the forecasting model, and performing online correction on the forecasting model. Otherwise, the model parameters are considered to be accurate, and no online correction is required.
(3) Retraining the forecast model parameters, modeling the training process
Wherein E is the square error of the forecast result, ULFor the lower bound of the parameter vector to be estimated, UUIs the upper bound of the parameter vector to be estimated. The model is solved according to the following formula:
wherein ▽ E is a Jacobian matrix of E,is F aboutOf the Jacobian, λ is Lagrange multiplier, zLIs bound by the lower bound ULDetermined dual variable, zUIs bound by the beam upper bound UUA determined dual variable, the equation being equivalent to:
(U-UL)zL-μeL＝0 (19)
(UU-U)zU-μeU＝0 (20)
where μ is a barrier parameter, eLIs composed of zLLower bound of decision ULIndicator eUIs composed of zUConstraint upper bound U of decisionUAn indicator. The updating mode of mu is as follows:
wherein the subscript q denotes the loop iteration count, εtolFor a given error margin, the parameter kμ∈(0,1)、θμ∈(1,2)。
The invention has the following beneficial effects: 1. due to the adoption of the technical means of online correction, the frequency and the time axis of input data can be observed simultaneously to acquire data information under multiple scales, and production data in the propylene production process is fully utilized, so that the prediction precision can be improved; 2. due to the adoption of a multi-scale analysis technical means, the forecasting precision of the forecasting model can be monitored in real time, and when the forecasting model is mismatched and the precision is reduced, the parameters of the forecasting model are corrected on line, so that the forecasting anti-jamming capability can be improved.
Drawings
FIG. 1 is a schematic diagram of the basic structure of an on-line corrected multi-scale forecasting system for propylene polymerization production process;
fig. 2 is a schematic structural diagram of an online-corrected multi-scale forecasting system.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
Referring to fig. 2, an online-corrected multi-scale prediction system for propylene polymerization production process is used for performing melt index prediction on a propylene polymerization process 1, and comprises a data preprocessing module 7, a multi-scale analysis module 8, a prediction model module 9 and an online correction module 10.
Further, the input of the data preprocessing module 7 is 9 variables of the propylene polymerization production process 1Since each variable has different units, in order to prevent different dimensions from causing errors between data magnitudes, all data are normalized, and the normalization formula is as follows:
wherein mean is the arithmetic mean of each variable, std is the standard deviation of each variable,the subscript r is the value of the input variable, r is the detection of the r, s is the variable of the s dimension, xrsThe values of the normalized input variables are used as input data. Normalized data is S ═ xr1,xr2,...,xr9}。
Further, the multi-scale analysis module 8 observes the frequency and the time axis of the input data through multi-scale analysis, and has a better time resolution when the frequency is high and a better frequency resolution when the frequency is low, so as to obtain data information under multi-scale. Normalizing the data S to { x ═ xr1,xr2,...xr9Carry out multi-scale divisionThe precipitation treatment was as follows:
(1) representing the corresponding input data at the current scale J as SJAccording to the following formula to SJWavelet decomposition is performed, and the dimension J is reduced by 1:
wherein, J0In order to be the initial scale, the method comprises the following steps,is the coefficient sequence basis function and psi is the difference sequence basis function.Is scale J0The next k-th coefficient sequence basis function,is prepared by reacting withCorresponding weight coefficient,. psil,kIs the k-th difference sequence basis function at the scale l, dl,kIs equal to psil,kThe corresponding weight coefficients.
Wherein j is the jth scale,for the k-th coefficient sequence basis function at the scale j,is equal to time 2jAnd the t-k related coefficient sequence constant takes the following values:
wherein, t is the time,is a constant related to t. And defines:
wherein psi0,0(t) is a time-dependent constant,is equal to the dimension J0-1 k-th difference sequence basis functionThe corresponding weight coefficients. Thereby obtaining:
wherein d isj,kIs the k-th difference sequence basis function psi under the scale jj,kThe corresponding weight coefficients. When J is 1, stopping decomposition and obtaining a series of corresponding wavelet analysis coefficients d under the current scale J(l)＝{d1,d2,…dJ-1}。
(2) Updating the time segment T in the current iteration by interpolation(l)If its corresponding wavelet analysis coefficientThe following conditions are met:
the corresponding time segments are combined, where eeGiven a normal number.
(3) If its corresponding wavelet analysis coefficientThe following conditions are met:
further interpolation is performed on the corresponding time segment; so as to obtain a new optimized running time segment T(l +1)In which epsiloniGiven a normal number.
Further, the prediction model module 9 uses a statistical modeling method to perform a highly nonlinear mapping from the input parameters to the output melt index prediction values by minimizing an error function, and the mapping maintains a topological invariance:
where Γ represents an objective function, w represents inertial weights, ξ represents errors, C represents penalty factors, u represents weight coefficients, β represents kernel function mapping, b represents bias, x is input data, y is output data, subscript i represents ith data, n is the total number of output variables, and superscript T represents the transpose of the matrix.
Further, the online correction module 10 performs real-time correction on the parameters of the predictive model module 9 by using an online correction strategy, and adds the predictive data with a large predictive error as new training data into the training data set to correct the model error in real time:
(1) the online calibration module 10 obtains a calibration value of the measurement data so that it satisfies the material and energy balance relationship of the whole apparatus and unit equipment, while minimizing the weighted sum of squares of the difference between the measurement value and the calibration value.
MIp＝MIa+ε (12)
Wherein MI is melt index, MIpFor melt index measurements, MIaIs the true value of the melt index, epsilon is the error vector,for the correction values, U is the prediction model parameter vector,and F is a prediction model function vector which represents chemical and physical laws such as material balance, energy balance, chemical reaction metering relation and the like in the propylene polymerization process. The (n × n) order variance-covariance matrix, where Q is MI, can be estimated from the meter accuracy or measurement samples.
(2) When the online correction module 10 works, the analysis value MI at the moment t is obtained in real timea(t) and the predicted value MIp(t) calculating an analysis value MIaAnd predicted value MIpDeviation e ofo(t)：
eo(t)＝|MIa(t)－MIp(t)| (14)
If eo(t) greater than a positive error margin εo：
eo(t)＞εo(15)
The analysis value MI at the time point t is compareda(t) and parameter values x (t) as new training data { x (t), MIa(t) adding the training data set, and retraining the parameters of the forecasting model module 9 to perform online correction of the forecasting model. Otherwise, the model parameters are considered to be accurate, and no online correction is required.
(3) Retraining the parameters of the predictive model module 9, modeling the training process
Wherein E is the square error of the forecast result, ULFor the lower bound of the parameter vector to be estimated, UUIs the upper bound of the parameter vector to be estimated. The model is solved according to the following formula:
wherein ▽ E is a Jacobian matrix of E,is F aboutOf the Jacobian, λ is Lagrange multiplier, zLIs bound by the lower bound ULDetermined dual variable, zUIs bound by the beam upper bound UUA determined dual variable, the equation being equivalent to:
(U-UL)zL-μeL＝0 (19)
(UU-U)zU-μeU＝0 (20)
where μ is a barrier parameter, eLIs composed of zLLower bound of decision ULIndicator eUIs composed of zUConstraint upper bound U of decisionUAn indicator. The updating mode of mu is as follows:
wherein the subscript q denotes the loop iteration count, εtolFor a given error margin, the parameter kμ∈(0,1)、θμ∈(1,2)。
Referring to fig. 1, an on-site intelligent instrument 2 and a control station 3 are connected to a propylene polymerization production process 1 and to a database 4; the online correction multi-scale forecasting system 5 is connected with the database 4 and the forecasting result display instrument 6. The on-site intelligent instrument 2 measures the easily-measured variable of the propylene polymerization production process 1 and transmits the easily-measured variable to the database 4; the control station 3 controls the manipulated variables of the propylene polymerization production process 1, and transmits the manipulated variables to the database 4. The variable data recorded in the database 4 is used as the input of the online corrected multi-scale forecasting system 5, and the forecasting result display instrument 6 is used for displaying the output of the online corrected multi-scale forecasting system 5, namely the forecasting result.
According to the reaction mechanism and the process analysis, in consideration of various factors influencing the melt index in the production process of polypropylene, nine commonly used operation variables and easily-measured variables in the actual production process are taken as model input variables, including: three propylene feed flow rates, main catalyst flow rate, auxiliary catalyst flow rate, temperature, pressure, liquid level in the kettle, hydrogen volume concentration in the kettle, and the like.
TABLE 1 Online corrected input variables of model required by multiscale prediction system 5
Table 1 lists 9 model input variables, namely, the temperature in the kettle (T), the pressure in the kettle (p), the liquid level in the kettle (L) and the volume concentration of hydrogen in the kettle (X), which are input by the multi-scale forecasting system 5 for online correctionv) 3 propylene feed flow rates (first propylene feed flow rate f1, second propylene feed flow rate f2, third propylene feed flow rate f3), 2 catalyst feed flow rates (main catalyst flow rate f4, cocatalyst flow rate f 5). The polymerization reaction in the reaction kettle is carried out after reaction materials are repeatedly mixed, so that the process variable of the model input variable related to the materials adopts the average value of a plurality of previous moments. The data in this example were averaged over the previous hour. The melt index off-line test value is obtained by manual sampling and off-line test analysis, and is analyzed and collected every 4 hours.
The examples are intended to illustrate the invention, but not to limit the invention, and any modifications and variations of the invention within the spirit and scope of the claims are intended to fall within the scope of the invention.
Claims (5)
1. An on-line corrected multi-scale forecasting system for propylene polymerization production process, which is used for forecasting melt index of the propylene polymerization production process, and is characterized in that: the system comprises a data preprocessing module, a multi-scale analysis module, a forecasting model module and an online correction module.
2. The on-line corrected multi-scale forecasting system for propylene polymerization production process according to claim 1, characterized in that: the input of the data preprocessing module is 9 variables of the propylene polymerization production processSince each variable has different units, in order to prevent different dimensions from causing errors between data magnitudes, all data are normalized, and the normalization formula is as follows:
wherein mean is the arithmetic mean of each variable, std is the standard deviation of each variable,the subscript r is the value of the input variable, r is the detection of the r, s is the variable of the s dimension, xrsThe values of the normalized input variables are used as input data. Normalized data is S ═ xr1,xr2,...,xr9}。
3. The on-line corrected multi-scale forecasting system for propylene polymerization production process according to claim 1, characterized in that: the multi-scale analysis module simultaneously observes the frequency and the time axis of input data through multi-scale analysis, has better time resolution when the frequency is high, and has better frequency resolution when the frequency is low so as to acquire data information under multi-scale. Normalizing the data S to { x ═ xr1,xr2,...xr9Performing multi-scale analysis as follows:
(1) representing the corresponding input data at the current scale J as SJAccording to the following formula to SJWavelet decomposition is performed, and the dimension J is reduced by 1:
wherein, J0In order to be the initial scale, the method comprises the following steps,is the coefficient sequence basis function and psi is the difference sequence basis function.Is scale J0The next k-th coefficient sequence basis function,is prepared by reacting withCorresponding weight coefficient,. psil,kIs the k-th difference sequence basis function at the scale l, dl,kIs equal to psil,kThe corresponding weight coefficients.
Wherein j is the jth scale,for the k-th coefficient sequence basis function at the scale j,is equal to time 2jAnd the t-k related coefficient sequence constant takes the following values:
wherein, t is the time,is a constant related to t. And defines:
wherein psi0,0(t) is a time-dependent constant,is equal to the dimension J0-1 k-th difference sequence basis functionThe corresponding weight coefficients. Thereby obtaining:
wherein d isj,kIs the k-th difference sequence basis function psi under the scale jj,kThe corresponding weight coefficients. When J is 1, stopping decomposition and obtaining a series of corresponding wavelet analysis coefficients d under the current scale J(l)＝{d1,d2,…dJ-1}。
(2) Updating the time segment T in the current iteration by interpolation(l)If its corresponding wavelet analysis coefficientThe following conditions are met:
the corresponding time segments are combined, where eeGiven a normal number.
(3) If its corresponding wavelet analysis coefficientConform toThe following conditions were used:
further interpolation is performed on the corresponding time segment; so as to obtain a new optimized running time segment T(l+1)In which epsiloniGiven a normal number.
4. The on-line corrected multi-scale forecasting system for propylene polymerization production process according to claim 1, characterized in that: the forecasting model module uses a statistical modeling method to complete the highly nonlinear mapping from input parameters to output melt index forecasting values through error function minimization, and the mapping keeps topology invariance:
where Γ represents an objective function, w represents inertial weights, ξ represents errors, C represents penalty factors, u represents weight coefficients, β represents kernel function mapping, b represents bias, x is input data, y is output data, subscript i represents ith data, n is the total number of output variables, and superscript T represents the transpose of the matrix.
5. The on-line corrected multi-scale forecasting system for propylene polymerization production process according to claim 1, characterized in that: the online correction module adopts an online correction strategy to correct the parameters of the prediction model module in real time, and corrects the model error in real time by adding the prediction data with larger prediction error into a training data set as new training data:
(1) the online correction module obtains the correction value of the measurement data, so that the correction value meets the material and energy balance relation of the whole device and unit equipment, and the weighted square sum of the difference between the correction value and the measurement value is minimum.
MIp＝MIa+ε (12)
Wherein MI is melt index, MIpFor melt index measurements, MIaIs the true value of the melt index, epsilon is the error vector,for the correction values, U is the prediction model parameter vector,and F is a prediction model function vector which represents chemical and physical laws such as material balance, energy balance, chemical reaction metering relation and the like in the propylene polymerization process. The (n × n) order variance-covariance matrix, where Q is MI, can be estimated from the meter accuracy or measurement samples.
(2) When the on-line correction module works, the analysis value MI at the moment t is obtained in real timea(t) and the predicted value MIp(t) calculating an analysis value MIaAnd predicted value MIpDeviation e ofo(t)：
eo(t)＝|MIa(t)－MIp(t)| (14)
If eo(t) greater than a positive error margin εo：
eo(t)＞εo(15)
The analysis value MI at the time point t is compareda(t) and parameter values x (t) as new training data { x (t), MIaAnd (t) adding the training data set, retraining the parameters of the forecasting model, and performing online correction on the forecasting model. Otherwise, the model parameters are considered to be accurate, and no online correction is required.
(3) Retraining the forecast model parameters, modeling the training process
Wherein E is the square error of the forecast result, ULFor the parameter vector to be estimatedLower boundary, UUIs the upper bound of the parameter vector to be estimated. The model is solved according to the following formula:
wherein,a jacobian matrix of E is the,is F aboutOf the Jacobian, λ is Lagrange multiplier, zLIs bound by the lower bound ULDetermined dual variable, zUIs bound by the beam upper bound UUA determined dual variable, the equation being equivalent to:
(U-UL)zL-μeL＝0 (19)
(UU-U)zU-μeU＝0 (20)
where μ is a barrier parameter, eLIs composed of zLLower bound of decision ULIndicator eUIs composed of zUConstraint upper bound U of decisionUAn indicator. The updating mode of mu is as follows:
wherein the subscript q denotes the loop iteration count, εtolFor a given error margin, the parameter kμ∈(0,1)、θμ∈(1,2)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811625146.XA CN109726474B (en) | 2018-12-28 | 2018-12-28 | Online-correction multi-scale forecasting system for propylene polymerization production process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811625146.XA CN109726474B (en) | 2018-12-28 | 2018-12-28 | Online-correction multi-scale forecasting system for propylene polymerization production process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109726474A true CN109726474A (en) | 2019-05-07 |
| CN109726474B CN109726474B (en) | 2021-04-09 |
Family
ID=66297443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811625146.XA Expired - Fee Related CN109726474B (en) | 2018-12-28 | 2018-12-28 | Online-correction multi-scale forecasting system for propylene polymerization production process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726474B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113759834A (en) * | 2020-06-05 | 2021-12-07 | 中国石油天然气股份有限公司 | Chaos multi-scale intelligent optimal propylene polymerization process measuring instrument |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070005310A1 (en) * | 2005-06-29 | 2007-01-04 | Fujitsu Limited | Multi-scale analysis device |
| CN1916613A (en) * | 2006-09-12 | 2007-02-21 | 浙江大学 | Method for soft measuring fusion index in producing industrial polypropylene based on wavelet analysis |
| CN108804851A (en) * | 2018-06-28 | 2018-11-13 | 浙江大学 | A kind of high-precision propylene polymerization production process optimal soft survey instrument of chaos gunz optimizing |
| CN108873838A (en) * | 2018-06-28 | 2018-11-23 | 浙江大学 | A kind of propylene polymerization production process optimal soft survey instrument of gunz optimizing |
-
2018
- 2018-12-28 CN CN201811625146.XA patent/CN109726474B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070005310A1 (en) * | 2005-06-29 | 2007-01-04 | Fujitsu Limited | Multi-scale analysis device |
| CN1916613A (en) * | 2006-09-12 | 2007-02-21 | 浙江大学 | Method for soft measuring fusion index in producing industrial polypropylene based on wavelet analysis |
| CN108804851A (en) * | 2018-06-28 | 2018-11-13 | 浙江大学 | A kind of high-precision propylene polymerization production process optimal soft survey instrument of chaos gunz optimizing |
| CN108873838A (en) * | 2018-06-28 | 2018-11-23 | 浙江大学 | A kind of propylene polymerization production process optimal soft survey instrument of gunz optimizing |
Non-Patent Citations (5)
| Title |
|---|
| HUAQIN JIANG等: "《Prediction of the Melt Index Based on the Relevance Vector Machine with Modified Particle Swarm Optimization》", 《CHEMICAL ENGINEERING & TECHNOLOGY》 * |
| SHI JIAN等: "《Melt Index Prediction by Neural Soft-Sensor Based on Multi-Scale Analysis and Principal Component Analysis》", 《CHINESE JOURNAL OF CHEMICAL ENGINEERING 》 * |
| 施健: "《工业过程统计建模与监控方法研究》", 《中国优秀硕士学位论文全文数据库》 * |
| 林芯羽: "《基于多尺度的动态优化策略研究》", 《中国优秀硕士学位论文全文数据库》 * |
| 蒋华琴: "《智能支持向量机方法及其在丙烯聚合熔融指数预报中的应用》", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113759834A (en) * | 2020-06-05 | 2021-12-07 | 中国石油天然气股份有限公司 | Chaos multi-scale intelligent optimal propylene polymerization process measuring instrument |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109726474B (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101315557B (en) | Propylene polymerization production process optimal soft survey instrument and method based on genetic algorithm optimization BP neural network | |
| CN101630376B (en) | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process | |
| CN101382801B (en) | Optimum soft measuring instrument based on EGA-optimized polymerization of propylene production process and method | |
| CN101863088B (en) | Method for forecasting Mooney viscosity in rubber mixing process | |
| CN108804851A (en) | A kind of high-precision propylene polymerization production process optimal soft survey instrument of chaos gunz optimizing | |
| CN108982576A (en) | A kind of high-precision propylene polymerization production process optimal soft survey instrument of chaos | |
| CN102880809A (en) | Polypropylene melt index on-line measurement method based on incident vector regression model | |
| CN109507888B (en) | Propylene polymerization production process optimal online forecasting system based on ensemble learning | |
| CN103675011B (en) | The industrial melt index soft measurement instrument of optimum support vector machine and method | |
| CN108803525A (en) | A kind of quick high-precision propylene polymerization production process optimal soft survey instrument of chaos | |
| CN109711628B (en) | Online-correction self-adaptive multi-scale forecasting system for propylene polymerization production process | |
| CN109726474B (en) | Online-correction multi-scale forecasting system for propylene polymerization production process | |
| CN103823430A (en) | Intelligent weighing propylene polymerization production process optimal soft measurement system and method | |
| CN109507889A (en) | The propylene polymerization production process optimal online forecasting system of convolutional neural networks | |
| CN103675005B (en) | The industrial melt index soft measurement instrument of optimum FUZZY NETWORK and method | |
| CN103839103A (en) | BP optimal forecasting system and method in propylene polymerization production process | |
| CN108958181A (en) | A kind of propylene polymerization production process optimal soft survey instrument of agility | |
| CN103675010B (en) | The industrial melt index soft measurement instrument of support vector machine and method | |
| CN103675009B (en) | The industrial melt index soft measurement instrument of fuzzifying equation and method | |
| CN103955170A (en) | Propylene polymerization production process online forecasting system and method based on group intelligent optimization | |
| CN103838206A (en) | Optimal soft measurement meter and method in optimal BP multi-mode propylene polymerization production process | |
| CN101281182A (en) | Method for soft measuring sodium aluminate solution component concentration | |
| CN109829197A (en) | The propylene polymerization production process optimal soft survey instrument of improved cuckoo optimizing | |
| CN113764048B (en) | Polypropylene production quality on-line measuring system | |
| CN103838958A (en) | Vague intelligent optimal soft measuring instrument and method used in propylene polymerization production process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210409 Termination date: 20211228 |