CN112506050B - Intermittent process integration optimization method based on latent variable process migration model - Google Patents
Intermittent process integration optimization method based on latent variable process migration model Download PDFInfo
- Publication number
- CN112506050B CN112506050B CN202011218977.2A CN202011218977A CN112506050B CN 112506050 B CN112506050 B CN 112506050B CN 202011218977 A CN202011218977 A CN 202011218977A CN 112506050 B CN112506050 B CN 112506050B
- Authority
- CN
- China
- Prior art keywords
- batch
- data
- production process
- variable
- optimization
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 124
- 230000008569 process Effects 0.000 title claims abstract description 77
- 238000005457 optimization Methods 0.000 title claims abstract description 67
- 238000013508 migration Methods 0.000 title claims abstract description 24
- 230000005012 migration Effects 0.000 title claims abstract description 24
- 230000010354 integration Effects 0.000 title abstract description 10
- 238000004519 manufacturing process Methods 0.000 claims abstract description 58
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 239000000047 product Substances 0.000 claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 239000012467 final product Substances 0.000 claims abstract description 5
- 230000001502 supplementing effect Effects 0.000 claims abstract description 4
- 238000010923 batch production Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 7
- 230000017105 transposition Effects 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000010606 normalization Methods 0.000 abstract 1
- MULYSYXKGICWJF-UHFFFAOYSA-L cobalt(2+);oxalate Chemical compound [Co+2].[O-]C(=O)C([O-])=O MULYSYXKGICWJF-UHFFFAOYSA-L 0.000 description 24
- 239000002245 particle Substances 0.000 description 9
- VBIXEXWLHSRNKB-UHFFFAOYSA-N ammonium oxalate Chemical compound [NH4+].[NH4+].[O-]C(=O)C([O-])=O VBIXEXWLHSRNKB-UHFFFAOYSA-N 0.000 description 8
- 239000013078 crystal Substances 0.000 description 5
- 238000002425 crystallisation Methods 0.000 description 5
- 230000008025 crystallization Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- GUTLYIVDDKVIGB-UHFFFAOYSA-N cobalt atom Chemical compound [Co] GUTLYIVDDKVIGB-UHFFFAOYSA-N 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- MUBZPKHOEPUJKR-UHFFFAOYSA-N Oxalic acid Chemical compound OC(=O)C(O)=O MUBZPKHOEPUJKR-UHFFFAOYSA-N 0.000 description 3
- GVPFVAHMJGGAJG-UHFFFAOYSA-L cobalt dichloride Chemical compound [Cl-].[Cl-].[Co+2] GVPFVAHMJGGAJG-UHFFFAOYSA-L 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000010946 mechanistic model Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000003756 stirring Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 239000012847 fine chemical Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 235000006408 oxalic acid Nutrition 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An intermittent process integration optimization method based on a latent variable process migration model is used for acquiring data information of a new production process B and an old production process A and expanding a two-dimensional data matrix to acquire Xa、Ya、Xb、Yb(ii) a Carrying out normalization processing on the data matrixes of the production processes A and B, and establishing a process migration model; constructing an optimization problem and solving an optimal solution x in the B production processb(k) *(ii) a Setting n decision points for an operation variable x in a single batch operation period, and dividing the decision points into n +1 sections; when the ith decision point is reached, judging whether data is missing or not, forming an input vector at the decision point, supplementing unknown data, and estimating a future operation variable track; judging whether disturbance exists at the decision point i or not, and calculating a new control profile by the disturbance; to the operation variable
Updating the compensation, and optimizing the compensated solution
Filtering is carried out; the final product quality was obtained and the k +1 th batch was run using the new control profile. The method is favorable for improving the production quality of the product.
Description
Technical Field
The invention belongs to the field of optimization control of an intermittent process in an industrial production process, and particularly relates to an intermittent process integration optimization method based on a latent variable process migration model.
Background
A batch process, also referred to as a batch process, is an industrial process in which raw materials are processed into specific products according to a given process flow. Because the production process of the intermittent process is simple, and has the characteristics of great flexibility and low investment cost, the intermittent process is widely applied to the fields of fine chemistry industry, biological pharmacy, food production, metal processing and the like in modern industrial production. With increasing consumer demand and changing market conditions, it is important to optimize the process operation of batch processes. At this stage, many fine chemicals, biomedicines, food manufacturing and semiconductors are mass-produced, and there is a strong demand for improving the quality of these products to maximize the economic efficiency of factories. Therefore, batch process quality optimization methods are the key targets of current research.
An important research direction in the past decades with regard to batch process optimization methods is optimization based on mechanistic models. However, it takes a lot of time and effort to build a mechanistic model of a batch process, and in many cases, building a mechanistic model often encounters a problem that the mechanistic relations in the model are invalid, which results in the final effect of model optimization being far below or beyond the expected effect. Over decades of development, data-driven modeling methods and the related latent variable techniques therein have been widely used in a variety of complex industrial processes.
However, modeling using conventional data-driven methods requires enough process data samples, and the sample data of one process can only be used for that process, and not for the other process, even if the two processes are similar and cannot be mixed. This is clearly a challenge for modeling new batch processes, since they are just put into production, run for a relatively short period, and do not allow sufficient data samples to be obtained. Therefore, the new process will face the problem of difficult modeling due to insufficient data, which needs to find new methods to solve.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an intermittent process integration optimization method based on an latent variable process migration model, which can solve the problem that a new process is difficult to model due to insufficient data, is beneficial to improving the production quality of products and can maximize the economic benefit of a factory.
In order to achieve the aim, the invention provides an intermittent process integration optimization method based on a latent variable process migration model, which is characterized in that a process migration model is established by utilizing data of A and B in two similar intermittent production processes, and batch-to-batch optimization are carried out on the process migration model; the method specifically comprises the following steps:
step 1: acquiring data information of two production processes of a new production process B and an old production process A, and unfolding a two-dimensional data matrix to obtain Xa、Ya、Xb、Yb；
Wherein, XaInputting a variable matrix for the old production process A;
Xbinputting a variable matrix for a new production process B;
Yaoutputting a variable matrix for the old production process A;
Yboutputting a variable matrix for the new production process B;
step 2: normalizing the data matrixes of the old production process A and the new production process B, and establishing a partial least square process migration model of the joint quality index by using the normalized data;
and step 3: constructing an optimization problem according to the formula (1) and solving the optimal solution x of the new production process Bb(k) *：
Wherein k represents the kth batch production process;
phi (x, y) represents a quality index;
g (x, y) represents a constraint;
x represents the input data of the current batch;
y represents the predicted output data of the current lot after linear correction
xLAnd xMMinimum and maximum values of the manipulated variables, respectively;
and 4, step 4: setting n decision points for x in a single batch running period, and dividing the decision points into n +1 sections;
and 5: when the ith decision point is reached, judging whether data is missing or not, forming an input vector at the decision point, supplementing unknown data by using a principal component analysis method, and predicting a future operation variable track;
step 6: judging whether disturbance exists at the decision point i, if so, calculating a new control profile according to a formula (2), otherwise, skipping the step;
wherein k isiAt decision point i, in the kth batch process;
Δ is the incremental sign;
t represents transposition;
q and R are iterative weighting matrices for tracking and controlling penalties at decision points;
λ is the weight coefficient of the soft constraint;
and 7: to the operation variable
Updating the compensation, and optimizing the compensated solution according to the formula (3)
Filtering is carried out;
wherein,
representing the operation variables after the intra-batch optimization and the inter-batch optimization;
xb(k)representing the operation variable after being readjusted by filtering;
i represents an identity matrix;
w represents a diagonal gain matrix;
and 8: the final product quality was obtained and the k +1 th batch was run using the new control profile.
The invention utilizes the data information of two similar intermittent processes and adopts a JYPLS method to establish a latent variable process migration model, and the model has the greatest advantage that the historical data migration of the old process is applied to the new intermittent production process, thereby solving the problem that the new process is difficult to model due to insufficient data. For the process migration model, the chemical principle and the physical principle between two similar intermittent processes are the same or similar, and data information in the old process can be migrated into the new process so as to assist the model establishment of the new process. It is noted that there is an inevitable difference between the process migration model and the actual process, i.e. the problem of model-to-process mismatch, which will also lead to a more serious problem of mismatch of optimal requirements (NCO) in model optimization. Furthermore, batch processes are inevitably subject to disturbances and various uncertainties such as temperature imbalances, operating variable surges, signal disturbances, etc. during operation. Aiming at the problem of difference between two similar processes and the problem of mismatch of NCO in a model, the invention provides an inter-batch optimization method; the method is provided for optimizing the interior of the batch aiming at the noise caused by disturbance and other reasons existing in the running period of the batch, so that the method can simultaneously solve the problems between batches and between batches. The method can lead the operation variable to the optimal set point after the sub-optimal solution optimized from batch to batch passes through the intra-batch optimization method, thereby changing the quality of the final product from sub-optimal to optimal.
Drawings
FIG. 1 is a flow chart of a cobalt oxalate crystallization process;
FIG. 2 is a flow chart of a batch process integration optimization method based on a latent variable process migration model according to the present invention;
FIG. 3 is a comparison graph of the cobalt oxalate particle size optimization results under the JYPLS model-based integrated optimization method and under the single batch-to-batch optimization method of the present invention;
figure 4 is a comparative graphical representation of the ammonium oxalate feed rates obtained using the integrated optimization algorithm.
Detailed Description
As shown in fig. 1 to 4, the invention provides an intermittent process integration optimization method based on latent variable process migration model, which utilizes data of a and B in two similar intermittent production processes to establish a process migration model, and performs batch-to-batch optimization and batch-to-batch optimization on the process migration model; the method specifically comprises the following steps:
step 1: acquiring data information of two production processes of a new production process B and an old production process A, and unfolding a two-dimensional data matrix to obtain Xa、Ya、Xb、Yb；
Wherein, XaInputting a variable matrix for the old production process A;
Xbinputting a variable matrix for a new production process B;
Yaoutputting a variable matrix for the old production process A;
Yboutputting a variable matrix for the new production process B;
step 2: normalizing the data matrixes of the old production process A and the new production process B, and establishing a Joint-Y Partial Least square (JYPLS) process migration model of a Joint quality index by utilizing the normalized data;
and step 3: constructing an optimization problem according to the formula (1) and solving the optimal solution x of the new production process Bb(k) *：
Wherein k represents the kth batch production process;
phi (x, y) represents a quality index;
g (x, y) represents a constraint;
x represents the input data of the current batch;
y represents the predicted output data of the current lot after linear correction
xLAnd xMMinimum and maximum values of the manipulated variables, respectively;
and 4, step 4: setting n decision points for x in a single batch running period, and dividing the decision points into n +1 sections;
and 5: when the ith decision point is reached, judging whether data is missing or not, forming an input vector at the decision point, supplementing unknown data by using a Principal Component Analysis (PCA) method, and estimating a future operation variable track;
step 6: judging whether disturbance exists at the decision point i, if so, calculating a new control profile according to a formula (2), otherwise, skipping the step;
wherein k isiAt decision point i, in the kth batch process;
Δ is the incremental sign;
t represents transposition;
q and R are iterative weighting matrices for tracking and controlling penalties at decision points;
λ is the weight coefficient of the soft constraint;
and 7: to the operation variable
Updating the compensation, and optimizing the compensated solution according to the formula (3)
Filtering is carried out;
wherein,
indicating subject to intra-batch optimization and batchingOperating variables after secondary optimization;
xb(k)representing the operation variable after being readjusted by filtering;
i represents an identity matrix;
w represents a diagonal gain matrix;
and 8: the final product quality was obtained and the k +1 th batch was run using the new control profile.
The technical solution of the present invention will be described in more detail by the following specific examples.
In the industrial production of hard alloy, the quality standard of cobalt powder is higher and higher, which not only requires that the particle size of cobalt powder reaches the standard, but also requires that the particle size distribution meeting the standard should be relatively concentrated. The most important material for producing the cobalt powder is cobalt oxalate, the cobalt oxalate determines the granularity and the shape of the cobalt powder to a great extent, and the cobalt oxalate has high correlation, so that the optimization of the size of the cobalt oxalate crystal and the improvement of the production efficiency have important significance, and the implementation method is suitable for the crystallization process of the cobalt oxalate.
The cobalt oxalate crystallization process is typically a batch process resulting from the reaction of cobalt chloride and ammonium oxalate. The technological process is shown in figure 1, and the synthesis process includes two main parts, one is ammonium oxalate dissolver and the other is reaction kettle, and the ammonium oxalate solution is heated with steam and stirred constantly at constant stirring rate when the temperature reaches proper reaction temperature. The temperature was kept constant using a heating mantle and a PI controller.
The specific procedure of the cobalt oxalate crystallization process mainly comprises four steps: (1) preparing oxalic acid; (2) preparing ammonium oxalate; (3) synthesizing cobalt oxalate; (4) and (5) performing filter pressing, washing and drying.
In view of the analysis of the actual production process of cobalt oxalate, we chose 5 process parameters: reaction temperature, stirring rate, ammonium oxalate concentration, cobalt chloride concentration and initial volume of cobalt chloride; 1 process variable: ammonium oxalate flow rate; 1 output variable: the granularity of cobalt oxalate. These selected parameters and variables are used to predict cobalt oxalate quality.
TABLE 1 parameter and variable table
The intermittent process integration optimization method based on the process migration model is shown in FIG. 2:
1) JYPLS model building and data generation
The crystallization of cobalt oxalate was simulated using MATLAB version R2017 a. Firstly, analyzing the mechanism process of the cobalt oxalate, then establishing a mechanism model, and replacing the actual production process with the mechanism model so as to generate modeling data. In MATLAB, let old production run a produce 45 batches of data, use 5 of which to build a model, the remaining 40 batches of data to test the model; and (4) generating 40 batches of data in the new production process B, and establishing a cobalt oxalate granularity model. The JYPLS model was constructed using 5 lots of old production process a data representing an old process and 40 lots of B process data, and then examined using the remaining 40 lots of a process data, where the new production process B represents a new process.
2) Modified adaptive batch-to-batch optimization
Because the model has the problem of NCO mismatching, the batch-to-batch optimization is carried out on the output effect of the cobalt oxalate particle size by adopting a correction self-adaptive strategy. The correction self-adaptive strategy mainly utilizes the deviation between the predicted value and the actual measured value and the deviation of the derivative thereof to continuously correct the objective function and the constraint condition, thereby obtaining the optimal solution, namely the optimal operation track of the actual process. At first, the data samples of the new production process are less, but the data in the new process is expanded continuously as the production batches are increased continuously, and the model precision predicted by adopting the JYPLS method is gradually improved along with the iteration of the batch process. FIG. 3 shows the optimization result of cobalt oxalate particle size under the batch-to-batch optimization method based on the JYPLS model. In addition, the optimal average crystal size and the optimal manipulated variable trajectory calculated using Genetic Algorithm (GA) are also shown in fig. 3 and 4.
3) In-batch optimization of MCC (Mid-Course Correction, MCC) process
Due to the disturbance problem existing during the operation of a single batch, the batch-to-batch optimization method is represented by stranded conditions, which can cause the final quality of the product to exceed the defined control region, so that the batch-to-batch optimization is a sub-optimal solution, and therefore the MCC batch-to-batch optimization method is adopted. In the MCC method, a single intermittent process is divided into a plurality of stages by using a plurality of decision points, and the optimization of the operation in batches is carried out. The method mainly comprises the steps that when an intermittent process reaches a decision point from the beginning of operation, whether data are missing or not is judged at the decision point, if the data are incomplete, the obtained information is combined with supplemented information to fill the missing data, and then product quality is predicted and optimization action for solving the interference problem is executed. The MCC strategy mainly uses the square minimization of the error between the actual value and the predicted value to obtain the optimal solution, that is, the optimal operation track of the ammonium oxalate flow rate in the actual production process of cobalt oxalate.
4) Method for integrating batch-to-batch and batch-to-batch optimization
In MATLAB, an integrated optimization method combining batch-to-batch optimization and batch-to-batch optimization is adopted to perform optimization simulation on the output result of the cobalt oxalate with the particle size. FIG. 3 shows the optimization result of cobalt oxalate particle size under the JYPLS model-based integrated optimization method. Meanwhile, the results of the batch-to-batch optimization of the cobalt oxalate particle size are also shown in fig. 3, so that the two optimization effects are compared. It can be seen from the figure that the optimized curve between batches has large fluctuation, the internal disturbance can not be solved, and the integrated optimized effect has relatively stable curve because the problem of interference in the operation of a single batch can be overcome. Furthermore, the results of the batch-to-batch optimization did not reach the optimum average crystal size calculated using GA at the 35 th batch, whereas the integrated optimization method was reached already at the 20 th batch and exceeded the optimum average crystal size until the end of the batch run, whereas the results of the batch-to-batch optimization had a large fluctuation, even at the 40 th batch, below the optimum average crystal size calculated using GA. Furthermore, a comparison of the traces of the manipulated variables is shown in FIG. 4, from which it can be seen that both the batch-to-batch optimization and the integrated optimization based on the JYPLS model represent convergence compared to the manipulated variables obtained from the initial batch. However, it can be seen from fig. 4 that the convergence trend of the optimal solution obtained by the integration optimization is more obvious. Therefore, in the simulation, the deviation between the non-optimal operation variable and the actual optimal solution can be iteratively corrected by the proposed optimization method, so as to further compensate the mismatch between the model and the object.
According to the simulation results, the invention combines two similar processes to establish a prediction model of the cobalt oxalate, and transfers appropriate data information in the old process to the new process, and on the basis, an integrated optimization method is provided to improve the particle size of the cobalt oxalate to a higher level. After each batch is finished, the JYPLS method updates the next batch by using the data generated by the previous batch, thereby achieving the effect of improving the prediction precision of the model and achieving the purpose of updating the model. The field operator can adjust and improve the production strategy of the batch process in time by means of the result of model prediction, thereby improving the production efficiency. In addition, in order to overcome the problem of NCO mismatching in the model, a correction self-adaptive batch-to-batch optimization method is adopted; to overcome the problem of disturbances during the run of a single batch, batch-to-batch and batch-to-batch optimization methods are used. Finally, the control and optimization performance of the intermittent process can be improved through simulation verification.
Claims (1)
1. An intermittent process integrated optimization method based on a latent variable process migration model is characterized in that a process migration model is established by utilizing data of A and B in two similar intermittent production processes, and batch-to-batch optimization are carried out on the process migration model; the method specifically comprises the following steps:
step 1: acquiring data information of two production processes of a new production process B and an old production process A, and unfolding a two-dimensional data matrix to obtain Xa、Ya、Xb、Yb；
Wherein, XaInputting a variable matrix for the old production process A;
Xbinputting a variable matrix for a new production process B;
Yaoutputting a variable matrix for the old production process A;
Yboutputting a variable matrix for the new production process B;
step 2: normalizing the data matrixes of the old production process A and the new production process B, and establishing a partial least square process migration model of the joint quality index by using the normalized data;
and step 3: constructing an optimization problem according to the formula (1) and solving the optimal solution x of the new production process Bb(k) *：
Wherein k represents the kth batch production process;
phi (x, y) represents a quality index;
g (x, y) represents a constraint;
x represents the input data of the current batch;
y represents the predicted output data of the current lot after linear correction
xLAnd xMMinimum and maximum values of the manipulated variables, respectively;
and 4, step 4: setting n decision points for x in a single batch running period, and dividing the decision points into n +1 sections;
and 5: when the ith decision point is reached, judging whether data is missing or not, forming an input vector at the decision point, supplementing unknown data by using a principal component analysis method, and predicting a future operation variable track;
step 6: judging whether disturbance exists at the decision point i, if so, calculating a new control profile according to a formula (2), otherwise, skipping the step;
wherein k isiAt decision point i, in the kth batch process;
Δ is the incremental sign;
t represents transposition;
q and R are iterative weighting matrices for tracking and controlling penalties at decision points;
λ is the weight coefficient of the soft constraint;
and 7: to the operation variable
Updating the compensation, and optimizing the compensated solution according to the formula (3)
Filtering is carried out;
wherein,
representing the operation variables after the intra-batch optimization and the inter-batch optimization;
xb(k)representing the operation variable after being readjusted by filtering;
i represents an identity matrix;
w represents a diagonal gain matrix;
and 8: the final product quality was obtained and the k +1 th batch was run using the new control profile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011218977.2A CN112506050B (en) | 2020-11-04 | 2020-11-04 | Intermittent process integration optimization method based on latent variable process migration model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011218977.2A CN112506050B (en) | 2020-11-04 | 2020-11-04 | Intermittent process integration optimization method based on latent variable process migration model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112506050A CN112506050A (en) | 2021-03-16 |
| CN112506050B true CN112506050B (en) | 2021-12-03 |
Family
ID=74955166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011218977.2A Active CN112506050B (en) | 2020-11-04 | 2020-11-04 | Intermittent process integration optimization method based on latent variable process migration model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112506050B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110341B (en) * | 2021-04-21 | 2022-03-25 | 中国矿业大学 | Batch process layered optimization method based on latent variable process migration model |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339040B (en) * | 2010-07-15 | 2013-06-19 | 清华大学 | Optimization and control method of rectification column |
| CN105334831B (en) * | 2015-11-24 | 2017-10-24 | 江南大学 | The double dimension method for on-line optimization of batch process driven by data difference |
| CN105487515B (en) * | 2015-12-29 | 2018-01-16 | 浙江工业大学 | A kind of integrated optimization method for continuously stirring the technological design of autoclave course of reaction and control |
| CN109783772B (en) * | 2017-11-14 | 2023-12-22 | 贵州中烟工业有限责任公司 | Method for determining partial least square regression latent variable number |
| CN108388218B (en) * | 2018-02-08 | 2020-06-19 | 中国矿业大学 | Correction self-adaptive batch process optimization method based on latent variable process migration model |
| CN110426956B (en) * | 2019-07-30 | 2021-07-23 | 中国矿业大学 | Intermittent process optimal compensation control strategy based on process migration model |
| CN110609476B (en) * | 2019-09-19 | 2022-04-12 | 太原理工大学 | Multivariate nonlinear dynamic system model prediction control method based on Gaussian process model |
| CN110794782A (en) * | 2019-11-08 | 2020-02-14 | 中国矿业大学 | Batch industrial process online quality prediction method based on JY-MKPLS |
| CN111679643B (en) * | 2020-06-28 | 2021-10-15 | 中国矿业大学 | Intermittent process second-order correction self-adaptive optimization method based on process migration model |
-
2020
- 2020-11-04 CN CN202011218977.2A patent/CN112506050B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112506050A (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110426956B (en) | Intermittent process optimal compensation control strategy based on process migration model | |
| US8002871B2 (en) | Methods and apparatus for an oxygen furnace quality control system | |
| CN113110341B (en) | Batch process layered optimization method based on latent variable process migration model | |
| CN111679643B (en) | Intermittent process second-order correction self-adaptive optimization method based on process migration model | |
| CN112506050B (en) | Intermittent process integration optimization method based on latent variable process migration model | |
| CN108388218B (en) | Correction self-adaptive batch process optimization method based on latent variable process migration model | |
| CN109240362A (en) | A kind of method for adjusting pH value of waste water based on Fractional Order PID Controller | |
| CN113065288A (en) | Nutrient optimization method for compound fertilizer production based on industrial data and process mechanism | |
| CN116861224B (en) | Intermittent process soft measurement modeling system based on intermittent process soft measurement modeling method | |
| CN102902201B (en) | A kind of decoupled state spatial prediction control method of chemical industry multivariable process | |
| CN109635465B (en) | Batch operation track adjusting method based on TPLS model | |
| JP2004348481A (en) | Process control unit and method | |
| CN110597055A (en) | Uncertainty-resistant 2D piecewise affine intermittent process minimum-maximum optimization prediction control method | |
| CN114265312B (en) | Intermittent process layering optimization method based on twin-generation self-migration model | |
| CN108829058B (en) | Fuzzy iterative learning control method for chemical batch process | |
| CN110991765B (en) | Monitoring method and device of industrial production prediction model and electronic equipment | |
| CN114237035A (en) | Prediction function control method based on simplified extended state space model | |
| Duran-Villalobos et al. | Iterative learning modelling and control of batch fermentation processes | |
| CN106971079B (en) | The coordination optimization setting method and device of heavy iron procedure exit ferrous ion concentration | |
| CN109491349B (en) | Batch running track and space adjusting method applied to continuous stirring reaction kettle | |
| CN117414785B (en) | Control method, device, equipment and medium of high-throughput reaction kettle for photoresist production | |
| CN113568309B (en) | On-line space-time control method for temperature field | |
| KR100642016B1 (en) | The optimizing method of PTAC batch process based on multivariate predictive control and program sequence logic | |
| CN107991875A (en) | A kind of control method of the Chemical Batch Process enhancing model based on fail-safe analysis | |
| CN109491347B (en) | Method for adjusting operation track in batch operation in penicillin fermentation 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 |