CN115629579A - CSTR system control method and device - Google Patents
CSTR system control method and device Download PDFInfo
- Publication number
- CN115629579A CN115629579A CN202211252946.8A CN202211252946A CN115629579A CN 115629579 A CN115629579 A CN 115629579A CN 202211252946 A CN202211252946 A CN 202211252946A CN 115629579 A CN115629579 A CN 115629579A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- material concentration
- continuous
- data set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000000463 material Substances 0.000 claims abstract description 79
- 238000005457 optimization Methods 0.000 claims abstract description 47
- 230000001276 controlling effect Effects 0.000 claims abstract description 11
- 230000001105 regulatory effect Effects 0.000 claims abstract description 9
- 238000012417 linear regression Methods 0.000 claims description 16
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 abstract description 3
- 239000002826 coolant Substances 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 239000000110 cooling liquid Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000002994 raw material Substances 0.000 description 3
- 239000000376 reactant Substances 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012824 chemical production Methods 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 229920002994 synthetic fiber Polymers 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
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
Abstract
The embodiment of the invention discloses a control method and a control device of a CSTR system, which are applied to regulating and controlling control parameters of the CSTR system. Firstly, historical data of a CSTR system at a plurality of continuous moments are obtained, a data set is established, the data set is split based on a tree model and state parameters in the historical data, and a plurality of data subsets are obtained. Then, a linear model of each data subset is established respectively to form a hierarchical linear model. And finally, acquiring real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment, solving a preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predicting to obtain the numerical value of the control parameters of the CSTR system at the next continuous moment. The control method and the control device provided by the embodiment of the invention can reduce the modeling time of the physical mathematical model of the system, and simultaneously can design different preset optimization problems according to different requirements of users so as to meet the regulation and control of CSTR system control parameters under different working conditions and structures.
Description
Technical Field
The invention belongs to the technical field of CSTR systems, and particularly relates to a control method and device of a CSTR system.
Background
The Continuous Stirred Tank Reactor (CSTR) system is the most commonly used Reactor for polymerization chemical reaction in the chemical industry, plays a very important role in core equipment of chemical production, and is widely applied to the industries of dye, food, medical reagent and synthetic material.
In a CSTR system, reactants are formed by flowing the reactants into the reactor at a constant flow rate, while the reactants exit the reactor at the same constant flow rate. After the reaction raw materials flow into the CSTR system, the reaction raw materials and materials stored in the reactor are completely mixed instantly through the strong stirring action in the reactor, so that the concentration and the temperature in the reactor are equal everywhere. Therefore, the CSTR system can effectively process the raw materials with high suspended solid content, and avoids the layering phenomenon of the materials.
The CSTR system comprises control parameters and state parameters, wherein the control parameters are used for controlling the CSTR system, and the state parameters are used for reflecting the state of the CSTR system. In early control of the CSTR system, a position-based control device composed of unit meters or PID (Proportional-Integral-Differential) control is mostly adopted, and the control mode is to regulate and control the control parameters of the CSTR system. However, since the chemical reaction process generally has strong nonlinearity and hysteresis, and the position-based control device and the PID control are more suitable for a system having a linear and precise mathematical model, the position-based control device and the PID control do not perform well in the CSTR system control. Therefore, a method and apparatus for fast and stable control of a CSTR system is needed.
Disclosure of Invention
The embodiment of the invention provides a control method and a control device of a CSTR system, which are used for solving the problem that the control parameters of the CSTR system cannot be quickly and stably regulated and controlled in the prior art.
In order to solve the technical problem, the embodiment of the invention discloses the following technical scheme: .
In a first aspect, some embodiments of the present disclosure provide a method for controlling a CSTR system, which is applied to regulate and control parameters of the CSTR system; the method comprises the following steps:
acquiring historical data of a CSTR system at a plurality of continuous moments and establishing a data set, wherein a preset time interval is arranged between every two adjacent continuous moments, and the historical data comprises control parameter data, state parameter data and material concentration data;
splitting the data set based on the tree model and the state parameters to obtain a plurality of data subsets;
respectively establishing a linear model of each data subset to form a layered linear model, wherein input variables of the layered linear model are control parameters and material concentration, and output variables of the layered linear model are material concentration;
collecting real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment, wherein the real-time data comprises data of control parameters, data of state parameters and data of material concentration;
and solving a preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predicting to obtain the numerical value of the control parameters of the CSTR system at the next continuous moment.
In a second aspect, some embodiments of the present disclosure provide a control device for a CSTR system, which is used for regulating and controlling control parameters of the CSTR system; the method comprises the following steps:
the CSTR system comprises a data set establishing unit, a data processing unit and a data processing unit, wherein the data set establishing unit is used for acquiring historical data of the CSTR system at a plurality of continuous moments and establishing a data set, a preset time interval is arranged between every two adjacent continuous moments, and the historical data comprises control parameter data, state parameter data and material concentration data;
the data set splitting unit is used for splitting the data set based on the tree model and the state parameters to obtain a plurality of data subsets;
the hierarchical linear model establishing unit is used for respectively establishing a linear model of each data subset to form a hierarchical linear model, wherein input variables of the hierarchical linear model are control parameters and material concentration, and output variables of the hierarchical linear model are material concentration;
the system comprises a real-time data acquisition unit, a data processing unit and a data processing unit, wherein the real-time data acquisition unit is used for acquiring real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment, and the real-time data comprises control parameter data, state parameter data and material concentration data;
and the control parameter prediction unit is used for solving the preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predicting to obtain the numerical value of the control parameters of the CSTR system at the next continuous moment.
The embodiment of the invention provides a control method and a control device of a CSTR system, which are applied to regulating and controlling control parameters of the CSTR system. Firstly, historical data of the CSTR system at a plurality of continuous moments are obtained, a data set is established, the data set is split based on a tree model and state parameters in the historical data, and a plurality of data subsets are obtained. Then, a linear model of each data subset is established respectively to form a hierarchical linear model. And finally, acquiring real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment, solving a preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predicting to obtain the numerical value of the control parameters of the CSTR system at the next continuous moment.
The control method and the control device provided by the embodiment of the invention are suitable for a CSTR system with nonlinearity and high hysteresis, can reduce the modeling time of a physical mathematical model of the system, and can realize accurate and effective estimation of the nonlinear system. Meanwhile, different preset optimization problems can be designed according to different requirements of users, so that the regulation and control of CSTR system control parameters with different working conditions and different structures can be met.
Drawings
FIG. 1 is a flow chart illustrating a method for controlling a CSTR system according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating step S102 in fig. 1 according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a split data set according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating the step S105 in fig. 1 according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a control device of a CSTR system according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
In the disclosed embodiment of the invention, the differential relationship of CSTR system material concentration is as follows:
wherein, ca is the concentration of the material; t is the tank internal temperature, tc is the coolant temperature, and T and Tc are the state parameters of the CSTR system; tr is the coolant reference temperature and is a control parameter for the CSTR system. According to the CSTR system relational expression, the CSTR system is a system with a strong nonlinear relation due to the existence of an exponential function, and the cooling liquid reference temperature Tr can realize the control of the material concentration Ca only by controlling the cooling liquid temperature Tc and the tank internal temperature T, so that the hysteresis inertia of the CSTR system is strong. Therefore, accurate control of the values of the control parameters of the CSTR system is important to obtain the desired material concentration.
Fig. 1 is a schematic flow chart of a control method of a CSTR system according to an embodiment of the present invention, which can be used for regulating and controlling control parameters of the CSTR system. As shown in fig. 1, the control method includes the steps of:
step S101: historical data of the CSTR system at a plurality of successive time instants is acquired and a data set is established.
Wherein, a preset time interval is arranged between every two adjacent continuous moments, the historical data comprises data of control parameters, data of state parameters and data of material concentration.
In a CSTR system, there are many kinds of state parameters and control parameters, and for the sake of understanding, the embodiments of the present invention are only described by taking the tank temperature, the coolant temperature, and the coolant reference temperature as examples. The state parameters of the CSTR system comprise the temperature in the tank and the temperature of the cooling liquid, and can be acquired by a sensor arranged on the CSTR system. The control parameter of the CSTR system is the coolant reference temperature.
The method comprises the steps of obtaining state parameters, control parameters and material concentration data of the CSTR system at a plurality of past continuous moments as historical data, wherein a preset time interval is arranged between every two adjacent continuous moments. In one embodiment of the present disclosure, historical data is obtained for a CSTR system at a plurality of successive time instances over the last five days, with a 1 minute time interval between adjacent successive time instances. For example, the history data at a certain time represents the state of the CSTR system within one minute from the time, and the history data at the next continuous time adjacent to the time represents the state of the CSTR system within the next minute.
And establishing a data set of the acquired historical data, wherein samples in the data set are state parameter values, control parameter values and material concentration values of the CSTR system at a continuous moment.
Step S102: the data set is split based on the tree model and the state parameters to obtain a plurality of data subsets.
In one embodiment of the present disclosure, as shown in FIG. 2, the following sub-steps may be employed to split a data set.
Step S1021: a plurality of branch nodes of the data set are determined based on a binary tree model.
In the embodiment disclosed by the invention, the input variable of the binary tree model is a state parameter, and the output variable is the material concentration. This step can be implemented as follows:
firstly, a binary tree model is established according to the following method, pre-splitting is carried out on a data set to be split, the pre-splitting only aims at determining branch nodes of the data set, and actual splitting is not carried out on the data set.
D 1 ＝(Y i ,Cv i )∈D|Cv i <a,i＝1,2,3...N
D 2 ＝(Y i ,Cv i )∈D|Cv i ≥a,i＝1,2,3...N
And selecting a sample corresponding to the SSE minimum value as the node a to be branched, namely selecting a plurality of samples of the data set to be split, trying one by one, and finally taking the sample adopted when the SSE minimum value is obtained as the node a to be branched.
D is a data set to be split, N is the total number of samples in the data set D to be split, a is a node of a branch to be determined of the data set D to be split, and Y i Outputting the data value of the variable Cv for the ith sample in the data set D to be split i Inputting the data value of a variable for the ith sample in a data set D to be split, D 1 And D 2 Two data subsets, c, generated after pre-splitting the data set D based on the node a to be branched 1 And c 2 Are respectively D 1 And D 2 The mean of the medium output variables.
Judging whether the number of samples of each data subset to be pre-split is greater than the preset total number of samples, for example, the preset total number of samples is 10, and judging whether the number of samples of each data subset to be pre-split is greater than 10.
If the number of the samples of each data subset to be split is larger than the total number of the preset samples, it indicates that the size of each data subset to be split is enough, and the current node to be branched can be used as a branch node a of the data set for finally splitting the data set. And then, continuously performing pre-splitting on each pre-split data subset by adopting the method until the scale of the pre-split data subset does not meet the requirement, namely the number of samples of the pre-split data subset is less than the total number of preset samples.
If the number of samples of each data subset to be pre-split is not greater than the total number of preset samples, or the number of samples of one of the data subsets to be pre-split is not greater than the total number of preset samples, the data subsets to be pre-split are not further pre-split, and the node to be determined which is adopted when the pre-splitting is carried out cannot be used as a branch node of the data set.
Step S1022: the data set is split into a plurality of data subsets with each branch node.
Splitting the data set into a plurality of data subsets D using all branch nodes determined in step S1021 i The specific splitting manner may refer to the description about the pre-splitting in the above embodiments. By way of example only, fig. 3 illustrates a simplified example, where rounded rectangles represent data sets to be split, and circles represent data subsets to be finally split.
The numerical values of the samples in each data subset are close, whereby the data set can be divided into a plurality of subsets according to the degree of similarity of the samples.
The data subset after the data set is split by the branch node can be represented as:
S＝{D 1 ,D 2 ,D 3 ......D k }
where S is a data set created from historical data, D i And k is the number of the data subsets, and the number of samples of each data subset is greater than the preset total number of samples.
Step S103: and respectively establishing a linear model of each data subset to form a hierarchical linear model.
Because the samples in each data subset have similarities, in the disclosed embodiment of the present invention, a linear model is established for each data subset, so that each linear model can be maximally adapted to the samples in the corresponding data subset.
After the linear models of each data subset are established, each linear model is combined to form a layered linear model, wherein input variables of the layered linear model are control parameters and material concentration, output variables of the layered linear model are material concentration, and each layer of the layered linear model is in one-to-one correspondence with the linear models of one data subset.
In one embodiment of the present disclosure, step S103 may be completed in the following manner.
And (I) respectively establishing a linear regression model of each data subset, wherein input variables of the linear regression model are numerical values of the control parameters and the material concentration at m +1 continuous moments, and output variables of the linear regression model are numerical values of the material concentration at corresponding m continuous moments and the next continuous moment.
In the embodiment of the present invention, the material concentration at a certain time is considered to be related to the control parameters of the CSTR system and the material concentration in a certain time period before the certain time, so that the linear regression model of each data subset is established to include the related parameters of the CSTR system in the previous time period.
For each data subset, a linear regression model was established as follows:
F t ＝A×F t-1 +B×U t-1
wherein t is the current time or a corresponding historical time in the historical data; a and B are coefficient matrixes in the linear regression model respectively, and the linear regression models of different data subsets have different coefficient matrixes; a is a i And b i Coefficients of coefficient matrices a and B, respectively; m is a preset number and is an observation length, namely m continuous moments; y is t-i A value representing an output variable at time t-i, i =1,2,3.. No., m, time t-i being the i-th consecutive time before the current time or the historical time; y is t Outputting the value of the variable for the current time or the historical time; xc t-i A value representing the input variable at time t-i, i =1,2,3.
And (II) fitting the linear regression model of each data subset to form a hierarchical linear model, wherein each layer in the hierarchical linear model corresponds to the linear regression model of one data subset one by one.
The layered linear model is shown as follows:
F t ＝A 1 ×F t-1 +B 1 ×U t-1 F∈D 1 ,U∈D 1
F t ＝A 2 ×F t-1 +B 2 ×U t-1 F∈D 2 ,U∈D 2
……
F t ＝A K ×F t-1 +B k ×U t-1 F∈D k ,U∈D k
wherein A is i 、B i Coefficient matrixes of the ith layer are respectively, and the coefficient matrixes in different layers are different; d i Is the ith data subset.
Step S104: real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment are collected.
Data of the current time and m consecutive times before the current time are acquired as real-time data by a sensor arranged on the CSTR system, wherein m is a preset number consistent with the embodiment. The real-time data comprises data of control parameters, data of state parameters and data of material concentration.
Step S105: and solving the preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predicting to obtain the numerical value of the control parameters of the CSTR system at the next continuous moment.
When real-time data is substituted into the hierarchical linear model, it is first determined to which layer in the hierarchical linear model the real-time data belongs, i.e., to which data subset the similarity of the real-time data is highest. And predicting the material concentration at a continuous time after the current time by using a corresponding linear regression model in the hierarchical linear model. In the embodiment of the invention, the predicted values of the material concentration and the predicted values of the control parameters at a plurality of continuous moments in the future are solved simultaneously together with the layered linear model by utilizing the preset optimization problem of the control parameters and the material concentration, so that the predicted control parameters can meet the optimization target of the preset optimization problem.
In one embodiment of the present disclosure, as shown in fig. 4, the following sub-steps may be adopted to implement step S105.
Step S1051: and substituting the real-time data into the layered linear model, and simultaneously solving the material concentration predicted values at a plurality of continuous moments after the current moment and the control parameter predicted values at a plurality of continuous moments after the current moment by adopting a genetic algorithm according to a preset optimization problem.
In one embodiment disclosed in the present invention, the genetic algorithm employs a meta-heuristic optimization algorithm, wherein three operators, selection, crossover and mutation, determine the performance of the genetic algorithm: the selection operator determines how to select the individuals generating the offspring, and generally speaking, the individuals with higher fitness have higher selection probability; the crossover operator defines the rule of information transmission between individuals, namely the mode of generating the next generation of individuals between individuals; the mutation operator is the embodiment of randomness in the genetic algorithm, and can enable individuals to break through the limitation of current search and generate individuals with brand new characteristics.
The meta-heuristic optimization algorithm can be simply understood as being implemented according to the following steps:
1. binary coding is carried out on the data characteristics;
2. initializing a population;
3. evaluating the fitness of individuals in the population;
4. selecting a plurality of individuals from the population with a certain probability;
5. performing cross operation on the selected individuals to generate next generation individuals;
6. reducing the variation of a sub-segment in the individual with a small probability, and then executing the steps 3-6 again until reaching the preset iteration number.
In one embodiment of the present disclosure, the step S1051 may be implemented as follows:
the predicted value of the material concentration at h continuous moments after the current moment t is expressed by the following formula:
wherein, t is the current time,
the predicted value of the material concentration at the ith continuous time after the current time t is i =1,2,3 \8230, h is a preset number and represents h continuous times after the current time, for example, h =10.
And according to the real-time data, the layered linear model and the predicted values of the control parameters, the material concentration at the future continuous time after the current time can be obtained.
The expression of the predicted value of the material concentration at h continuous moments after the current moment t is defined here so as to be substituted into a preset optimization problem, and the predicted value of the material concentration and the predicted value of the control parameter at the future moment are obtained by simultaneously solving the preset optimization problem.
Obtaining the reference value of the material concentration at h continuous moments after the current moment t, wherein the reference value is expressed by the following formula:
ref＝[r tp1 ,r t+2 ,...,r t+h ]
wherein r is t+i I =1,2,3, 8230, 8230h, h, which is the reference value of the material concentration at the ith continuous time after the current time t.
In one embodiment of the invention, a material concentration reference value of the CSTR system at a future continuous moment is preset, and the material concentration reference value can reflect a value which is expected to be reached by the material concentration at a future moment.
The preset optimization problem is as follows:
Opt＝min loss(result,ref)
wherein Opt is an optimization target of a preset optimization problem, and loss is a loss function of the optimization target Opt;
g and h are respectively the optimization conditions of the preset optimization problem, lower and upper are respectively the lower and upper bounds of the control parameter predicted value, g and h represent respectively inequality and equality constraint functions, incons and eqcons are respectively the inequality and equality constraint conditions of the optimization problem, Y is the predicted value of the concentration of the material to be solved in the optimization problem,
for the control parameter prediction value to be solved in the optimization problem, the expression is as follows:
wherein the content of the first and second substances,
the predicted value of the control parameter to be solved at the ith continuous time after the current time t is i =1,2,3 \8230; \823030h.
In practical applications, the optimization target and the optimization condition for presetting the optimization problem in the embodiment of the present invention may be set according to requirements of users, and are not limited to the modes listed in the above embodiments.
In one embodiment of the disclosure, a loss function of an optimization target is calculated by using an average square error MSE, and the calculation formula is as follows:
wherein, result [ i ] is a predicted value of the material concentration at the ith continuous time after the current time, ref [ i ] is a reference value of the material concentration at the ith continuous time after the current time, and i =1,2,3 \8230 \ 8230h. The preset optimization problem is to solve a control parameter predicted value and a material concentration predicted value by taking the minimum loss function as an optimization target.
In one particular embodiment of the present disclosure,
the optimization objectives are set as follows:
Opt＝min loss(result,ref)
the optimization conditions are set as follows:
wherein Y represents the concentration of the material to be solved in the preset optimization problem,
the control parameters to be solved in the preset optimization problem are shown, the formula shows that the material concentration must be between 0.35 and 0.65mol/L, and the reference temperature of the cooling liquid of the control parameters must be between 335 and 372K.
Step S1052: and determining the control parameter predicted value at the next continuous time at the current time as the value of the control parameter of the CSTR system at the next continuous time.
According to the solution of the preset optimization problem, the control parameter predicted values of h continuous moments can be obtained, the control parameter predicted value of the first moment, namely the control parameter predicted value of the next continuous moment t +1 of the current moment t, is determined as the numerical value of the control parameter of the CSTR system at the next continuous moment, so that the control parameter of the CSTR system is regulated and controlled, and the real value of the material concentration of the CSTR system at the next continuous moment is close to the expected reference value as much as possible.
Fig. 5 is a schematic structural diagram of a control device of a CSTR system according to an embodiment of the present invention, which is used for regulating and controlling control parameters of the CSTR system. As shown in fig. 5, the control device includes the following units:
the data set establishing unit 11 is configured to acquire historical data of the CSTR system at a plurality of continuous moments and establish a data set, a preset time interval is reserved between every two adjacent continuous moments, and the historical data comprises data of control parameters, data of state parameters and data of material concentration;
a data set splitting unit 12 configured to split the data set based on the tree model and the state parameters to obtain a plurality of data subsets;
a layered linear model establishing unit 13 configured to respectively establish a linear model of each data subset to form a layered linear model, wherein input variables of the layered linear model are control parameters and material concentrations, and output variables of the layered linear model are material concentrations;
the real-time data acquisition unit 14 is configured to acquire real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment, wherein the real-time data comprises data of control parameters, data of state parameters and data of material concentration;
and the control parameter prediction unit 15 is configured to solve a preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predict to obtain the numerical value of the control parameters of the CSTR system at the next continuous time.
It will be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principles of the present invention, and the present invention is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (8)
1. A control method of CSTR system is used for regulating and controlling the control parameters of CSTR system; the control method is characterized by comprising the following steps:
acquiring historical data of a CSTR system at a plurality of continuous moments and establishing a data set, wherein a preset time interval is arranged between every two adjacent continuous moments, and the historical data comprises control parameter data, state parameter data and material concentration data;
splitting the data set based on the tree model and the state parameters to obtain a plurality of data subsets;
respectively establishing a linear model of each data subset to form a layered linear model, wherein input variables of the layered linear model are control parameters and material concentration, and output variables of the layered linear model are material concentration;
collecting real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment, wherein the real-time data comprises control parameter data, state parameter data and material concentration data;
and solving a preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predicting to obtain the numerical value of the control parameters of the CSTR system at the next continuous moment.
2. The control method according to claim 1, wherein the splitting the data set based on the tree model and the state parameter to obtain a plurality of data subsets comprises:
determining a plurality of branch nodes of a data set based on a binary tree model, wherein input variables of the binary tree model are state parameters, and output variables of the binary tree model are material concentration;
splitting the data set into a plurality of data subsets with each of the branch nodes.
3. The control method of claim 2, wherein determining the plurality of branch nodes of the data set based on the binary tree model comprises:
establishing a binary tree model according to the following method, and pre-splitting a data set to be split:
D 1 ＝(Y i ,Cv i )∈D|Cv i <a,i＝1,2,3...N
D 2 ＝(Y i ,Cv i )∈D|Cv i ≥a,i＝1,2,3...N
selecting a sample corresponding to the SSE minimum value as a node a to be branched;
d is a data set to be split, N is the total number of samples in the data set D to be split, a is a node of a branch to be determined of the data set D to be split, and Y i For the value of the output variable, cv, in the ith sample of the data set D to be split i For the value of the input variable in the ith sample in the data set D to be split, D 1 And D 2 Two data subsets, c, generated after pre-splitting the data set D based on the node a to be branched 1 And c 2 Are respectively D 1 And D 2 Mean of medium output variables;
judging whether the number of samples of each data subset which is pre-split is larger than the total number of the preset samples,
if yes, taking the node to be branched as a branch node of the data set, and continuously performing pre-splitting on each data subset obtained by pre-splitting by adopting the method;
if not, stopping pre-splitting the data subset.
4. The control method according to claim 1, wherein the establishing of the linear model for each data subset separately constitutes a hierarchical linear model comprising:
respectively establishing a linear regression model of each data subset according to the following modes, wherein input variables of the linear regression model are numerical values of the control parameters and the material concentration at m +1 continuous moments, and output variables are numerical values of the material concentration at corresponding m continuous moments and the next continuous moment:
F t ＝A×F t-1 +B×U t-1
wherein t is the current time or a corresponding historical time in the historical data; a and B are coefficient matrixes in the linear regression model respectively, and the linear regression models of different data subsets have different coefficient matrixes; a is i And b i Coefficients of coefficient matrices a and B, respectively; m is a preset number, namely m continuous moments; y is t-i A value representing an output variable at a time t-i, i =1,2,3.. No., m, the time t-i being the i-th consecutive time before the current time or the historical time; y is t Outputting the value of the variable for the current time or the historical time; xc t-i A numerical value representing an input variable at time t-i, i =1,2,3.. M;
and fitting the linear regression model of each data subset to form a hierarchical linear model, wherein each layer in the hierarchical linear model is in one-to-one correspondence with the linear regression model of one data subset.
5. The control method according to claim 4, wherein the step of solving a preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model to predict the value of the control parameters of the CSTR system at the next continuous time comprises the following steps:
substituting the real-time data into the layered linear model, and simultaneously solving material concentration predicted values at a plurality of continuous moments after the current moment and control parameter predicted values at a plurality of continuous moments after the current moment by adopting a genetic algorithm according to a preset optimization problem;
and determining the control parameter predicted value at the next continuous time at the current time as the numerical value of the control parameter of the CSTR system at the next continuous time.
6. The control method according to claim 5, wherein the substituting real-time data into the hierarchical linear model and simultaneously solving the material concentration predicted values at a plurality of consecutive moments after the current moment and the control parameter predicted values at a plurality of consecutive moments after the current moment by using a genetic algorithm according to a preset optimization problem comprises:
the predicted value of the material concentration at h continuous moments after the current moment is expressed by the following formula:
wherein, t is the current time,
the predicted value of the material concentration at the ith continuous time after the current time t is that i =1,2, 3\8230, i 8230, h, h is a preset number;
obtaining the reference value of the material concentration at h continuous moments after the current moment, wherein the reference value is expressed by the following formula:
ref＝[r t+1 ,r t+2 ,...,r t+h ]
wherein r is t+i I =1,2,3, 8230, 8230h, h, which is the reference value of the material concentration at the ith continuous time after the current time t;
the preset optimization problem is as follows:
Opt＝min loss(result,ref)
wherein Opt is an optimization target of a preset optimization problem, loss is an Opt loss function, lower and upper are respectively a lower bound and an upper bound of a control parameter predicted value, g and h respectively represent inequality and equality constraint functions, incones and eqcons are respectively inequality and equality constraint conditions, Y is a predicted value of the concentration of the material to be solved in the preset optimization problem,
for the control parameter prediction value to be solved in the preset optimization problem, the following is expressed:
wherein, the first and the second end of the pipe are connected with each other,
and i =1,2,3, 8230, 8230h and h are predicted values of the control parameters to be solved at the ith continuous time after the current time t.
7. The control method according to claim 6, characterized by further comprising:
calculating a loss function of an optimization target by using the Mean Square Error (MSE), wherein the calculation formula is as follows:
wherein, result [ i ] is a predicted value of the material concentration at the ith continuous time after the current time, ref [ i ] is a reference value of the material concentration at the ith continuous time after the current time, and i =1,2,3 \8230 \ 8230h.
8. A control device of CSTR system is used for regulating and controlling the control parameters of CSTR system; characterized in that the control device comprises:
the CSTR system comprises a data set establishing unit, a data processing unit and a data processing unit, wherein the data set establishing unit is used for acquiring historical data of the CSTR system at a plurality of continuous moments and establishing a data set, a preset time interval is arranged between every two adjacent continuous moments, and the historical data comprises data of control parameters, data of state parameters and data of material concentration;
the data set splitting unit is used for splitting the data set based on the tree model and the state parameters to obtain a plurality of data subsets;
the hierarchical linear model establishing unit is used for respectively establishing a linear model of each data subset to form a hierarchical linear model, wherein input variables of the hierarchical linear model are control parameters and material concentration, and output variables of the hierarchical linear model are material concentration;
the system comprises a real-time data acquisition unit, a data processing unit and a data processing unit, wherein the real-time data acquisition unit is used for acquiring real-time data of the CSTR system at the current moment and a plurality of continuous moments before the current moment, and the real-time data comprises data of control parameters, data of state parameters and data of material concentration;
and the control parameter prediction unit is used for solving the preset optimization problem of the control parameters and the material concentration according to the real-time data and the layered linear model, and predicting to obtain the numerical value of the control parameters of the CSTR system at the next continuous moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211252946.8A CN115629579B (en) | 2022-10-13 | 2022-10-13 | Control method and device of CSTR system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211252946.8A CN115629579B (en) | 2022-10-13 | 2022-10-13 | Control method and device of CSTR system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115629579A true CN115629579A (en) | 2023-01-20 |
| CN115629579B CN115629579B (en) | 2023-11-07 |
Family
ID=84905678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211252946.8A Active CN115629579B (en) | 2022-10-13 | 2022-10-13 | Control method and device of CSTR system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115629579B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420796A (en) * | 2008-12-02 | 2009-04-29 | 郭震 | A kind of heating power device |
| CN103927506A (en) * | 2014-04-25 | 2014-07-16 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | RIFD anti-collision method based on dynamic timeslot conflict tracking tree |
| CN107533995A (en) * | 2015-05-08 | 2018-01-02 | 科磊股份有限公司 | Hot spot monitoring based on model |
| CN109214117A (en) * | 2018-10-15 | 2019-01-15 | 南京天洑软件有限公司 | A kind of intelligent industrial algorithm for design based on value network |
| CN109997154A (en) * | 2017-10-30 | 2019-07-09 | 上海寒武纪信息科技有限公司 | Information processing method and terminal device |
| US20200183378A1 (en) * | 2018-12-06 | 2020-06-11 | Schneider Electric Systems Usa, Inc. | Systems and methods for automatically collecting and analyzing data from industrial equipment |
| CN112308273A (en) * | 2019-07-31 | 2021-02-02 | 中国石油化工股份有限公司 | Memory, petrochemical enterprise pollution discharge management method, device and equipment |
| WO2021080824A1 (en) * | 2019-10-25 | 2021-04-29 | Dow Global Technologies Llc | Nonlinear model predictive control of a process |
| US20220058317A1 (en) * | 2020-08-23 | 2022-02-24 | Ricardo Reis De Carvalho | Smart process control system for continuous treatment of felts |
-
2022
- 2022-10-13 CN CN202211252946.8A patent/CN115629579B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420796A (en) * | 2008-12-02 | 2009-04-29 | 郭震 | A kind of heating power device |
| CN103927506A (en) * | 2014-04-25 | 2014-07-16 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | RIFD anti-collision method based on dynamic timeslot conflict tracking tree |
| CN107533995A (en) * | 2015-05-08 | 2018-01-02 | 科磊股份有限公司 | Hot spot monitoring based on model |
| CN109997154A (en) * | 2017-10-30 | 2019-07-09 | 上海寒武纪信息科技有限公司 | Information processing method and terminal device |
| CN109214117A (en) * | 2018-10-15 | 2019-01-15 | 南京天洑软件有限公司 | A kind of intelligent industrial algorithm for design based on value network |
| US20200183378A1 (en) * | 2018-12-06 | 2020-06-11 | Schneider Electric Systems Usa, Inc. | Systems and methods for automatically collecting and analyzing data from industrial equipment |
| CN112308273A (en) * | 2019-07-31 | 2021-02-02 | 中国石油化工股份有限公司 | Memory, petrochemical enterprise pollution discharge management method, device and equipment |
| WO2021080824A1 (en) * | 2019-10-25 | 2021-04-29 | Dow Global Technologies Llc | Nonlinear model predictive control of a process |
| US20220058317A1 (en) * | 2020-08-23 | 2022-02-24 | Ricardo Reis De Carvalho | Smart process control system for continuous treatment of felts |
Non-Patent Citations (3)
| Title |
|---|
| LO S N: "Optimization of output fluctuation model of non-ideal CSTR\'s in series with a sinusoidal input of concentration", 《CHEMICAL ENGINEERING SCIENCE》 * |
| 孙浩鹏;: "面向Fluent的PABR反应器三维模型分割方法", 科技创新与应用, no. 27 * |
| 李成, 宋执环, 李平: "基于小波域隐马尔可夫树模型的过程趋势分析", 信息与控制, no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115629579B (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100458607C (en) | Method of soft measuring fusion index of producing propylene through polymerization in industrialization | |
| CN112987664B (en) | Flow shop scheduling method based on deep reinforcement learning | |
| CN110202768B (en) | Temperature control method for charging barrel of injection molding machine | |
| CN103123460A (en) | Temperature control system and temperature control method | |
| JP3790129B2 (en) | Process simulator application control apparatus and method | |
| Bettenhausen et al. | Self-organizing structured modelling of a biotechnological fed-batch fermentation by means of genetic programming | |
| CN115629579B (en) | Control method and device of CSTR system | |
| Onu et al. | Artificial intelligence-based IoT-enabled biogas production | |
| Marenbach et al. | Data-driven structured modelling of a biotechnological fed-batch fermentation by means of genetic programming | |
| Campos et al. | PD+ I Fuzzy Controller optimized by PSO applied to a variable dead time process | |
| CN112016241A (en) | Soft measurement modeling method based on mLASSO-MLP model | |
| Lin et al. | Data-driven state transition algorithm for fuzzy chance-constrained dynamic optimization | |
| Hosen et al. | Prediction interval-based modelling of polymerization reactor: A new modelling strategy for chemical reactors | |
| CN115097737B (en) | Multi-level regulation and control method capable of being re-entered into manufacturing system | |
| Soukkou et al. | Optimal control of a CSTR process | |
| CN110794676A (en) | CSTR process nonlinear control method based on Hammerstein-Wiener model | |
| CN102759602A (en) | Method for predicting faults in cascade polymerization reaction process of high density polyethylene (HDPE) | |
| Zhang et al. | Optimization control of a fed-batch process using an improved reinforcement learning algorithm | |
| Özalp et al. | Physics-informed long short-term memory for forecasting and reconstruction of chaos | |
| CN106127326B (en) | Chemical material processing melt index forecasting method | |
| CN105487380B (en) | A kind of distributed control method of Multi-stage stirring reactor | |
| CN203217277U (en) | Non-linear model predication controller of tank reactor based on online support vector machine | |
| Willis et al. | Developing inferential estimation algorithms using genetic programming | |
| Sreram et al. | Estimating random delays in Modbus over TCP/IP network using experiments and general linear regression neural networks with genetic algorithm smoothing | |
| CN113779865B (en) | Modeling method and device for steam thermal cracking process, electronic equipment and readable storage medium thereof |
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 |