Constrained optimization method and device for objective function corresponding to cement production process model

By performing multiple iterative optimization of the objective function of the cement production process model and updating the independent variable group, the efficiency problem of objective function constraint optimization in the cement production process model is solved, and the accuracy of output information and model verification efficiency are improved.

CN113449433BActive Publication Date: 2024-12-03ZHONGCUN BIG DATA TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110808431.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-16
Publication Date
2024-12-03
Estimated Expiration
2041-07-16

AI Technical Summary

Technical Problem

In the cement production process, how to efficiently optimize the objective function corresponding to the cement production process model to ensure the accuracy of the output information.

Method used

By obtaining the objective function and initial independent variable group corresponding to the cement production process model, using the preset optimization algorithm to perform multiple iteration optimization, we will determine whether the independent variable group of each iteration is located in the preset feasible domain. If it is there, it will stop or continue to optimize. If not, the iterative independent variable group is updated until the preset stop condition is reached.

Benefits of technology

It realizes efficient constraint optimization of the objective function of the cement production process model, and improves the accuracy of output information and model verification efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113449433B_ABST
    Figure CN113449433B_ABST
Patent Text Reader

Abstract

The present application discloses a method and device for constrained optimization of an objective function corresponding to a cement production process model, and relates to the technical field of cement production. The method of the present application comprises: obtaining an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function contains a plurality of objective independent variables, and the initial independent variable group contains an initial setting value corresponding to each of the objective independent variables; performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of cement production, and in particular to a method and device for constrained optimization of an objective function corresponding to a cement production process model. Background Art

[0002] In the field of cement production technology, the cement production process model is used to simulate the preheater and rotary kiln. After the measured data such as the quality and composition of raw materials and coal are input into the cement production process model, the cement production process model can output information such as the outlet material of each equipment, flue gas flow, flue gas temperature and flue gas composition, thereby providing data support for the actual cement production.

[0003] In order to ensure the accuracy of the output information of the cement production process model, it is necessary to define the objective function corresponding to the function contained in the cement production process model, and perform constrained optimization on the defined objective function, so as to realize the verification of the cement production process model. Therefore, how to efficiently perform constrained optimization on the objective function corresponding to the cement production process model is crucial. Summary of the invention

[0004] The embodiments of the present application provide a method and device for constrained optimization of an objective function corresponding to a cement production process model, the main purpose of which is to efficiently perform constrained optimization on the objective function corresponding to the cement production process model.

[0005] In order to solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0006] In a first aspect, the present application provides a method for constrained optimization of an objective function corresponding to a cement production process model, the method comprising:

[0007] Obtaining an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function includes a plurality of objective independent variables, and the initial independent variable group includes an initial set value corresponding to each of the objective independent variables;

[0008] The objective function is optimized for multiple rounds of iterations according to the initial independent variable group and the preset optimization algorithm; wherein,

[0009] After each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the current round of optimization is within the preset feasible domain. If the current round of iterative independent variable group is within the preset feasible domain, it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the updated iterative independent variable group, wherein the historical iterative independent variable group is the current round of iterative independent variable group or the updated iterative independent variable group corresponding to the previous round of optimization.

[0010] Optionally, when there are maintenance parameters corresponding to the preset optimization algorithm, performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm includes:

[0011] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the current round parameter value corresponding to the maintenance parameter is calculated according to the current round gradient value corresponding to each of the target independent variables; the current round parameter value corresponding to the maintenance parameter, the initial setting value corresponding to each of the target independent variables and the current round gradient value are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space;

[0012] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; calculate the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each of the target independent variables; substitute the current round parameter value corresponding to the maintenance parameter, the historical iteration value corresponding to each of the target independent variables and the current round gradient value into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate the current round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter in the local storage space; wherein N is a positive integer.

[0013] Optionally, when there is no maintenance parameter corresponding to the preset optimization algorithm, performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm includes:

[0014] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the initial setting value and the current round gradient value corresponding to each of the target independent variables are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is stored in the local storage space;

[0015] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; substitute the historical iteration values ​​and current round gradient values ​​corresponding to each of the target independent variables into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate this round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group in the local storage space; wherein N is a positive integer.

[0016] Optionally, updating the historical iteration independent variable group according to the current round iteration independent variable group to obtain an updated iteration independent variable group includes:

[0017] The historical iteration independent variable group is updated multiple times according to the current iteration value corresponding to each target independent variable to obtain multiple intermediate iteration independent variable groups, and the intermediate iteration independent variable group obtained by the last round of updating is determined as the updated iteration independent variable group; wherein,

[0018] After each round of updating, it is determined whether the intermediate iterative independent variable group obtained in this round of updating is within the preset feasible domain. If the intermediate iterative independent variable group is within the preset feasible domain, the current round of updating is retained, and the next round of updating is performed based on the intermediate iterative independent variable group; if the intermediate iterative independent variable group is not within the preset feasible domain, the current round of updating is discarded, and the current round gradient value of the target independent variable corresponding to the current round of updating is updated to zero, and the next round of updating is performed.

[0019] Optionally, when there are maintenance parameters corresponding to the preset optimization algorithm, after updating the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group, the method further includes:

[0020] Calculate the current round update parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each target independent variable;

[0021] In the local storage space, the current round update parameter value corresponding to the maintenance parameter is updated using the current round update parameter value corresponding to the maintenance parameter.

[0022] In a second aspect, the present application further provides a constrained optimization device for a cement production process model corresponding to an objective function, the device comprising:

[0023] An acquisition unit, used for acquiring an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function includes a plurality of objective independent variables, and the initial independent variable group includes an initial setting value corresponding to each of the objective independent variables;

[0024] An optimization unit is used to perform multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm; wherein,

[0025] After each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the current round of optimization is within the preset feasible domain. If the current round of iterative independent variable group is within the preset feasible domain, it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the updated iterative independent variable group, wherein the historical iterative independent variable group is the current round of iterative independent variable group or the updated iterative independent variable group corresponding to the previous round of optimization.

[0026] Optionally, the optimization unit includes:

[0027] The first optimization module is used for, when there are maintenance parameters corresponding to the preset optimization algorithm,

[0028] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the current round parameter value corresponding to the maintenance parameter is calculated according to the current round gradient value corresponding to each of the target independent variables; the current round parameter value corresponding to the maintenance parameter, the initial setting value corresponding to each of the target independent variables and the current round gradient value are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space;

[0029] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; calculate the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each of the target independent variables; substitute the current round parameter value corresponding to the maintenance parameter, the historical iteration value corresponding to each of the target independent variables and the current round gradient value into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate the current round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter in the local storage space; wherein N is a positive integer.

[0030] Optionally, the optimization unit includes:

[0031] The second optimization module is used for, when there is no maintenance parameter corresponding to the preset optimization algorithm,

[0032] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the initial setting value and the current round gradient value corresponding to each of the target independent variables are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is stored in the local storage space;

[0033] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; substitute the historical iteration values ​​and current round gradient values ​​corresponding to each of the target independent variables into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate this round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group in the local storage space; wherein N is a positive integer.

[0034] Optionally, the optimization unit includes:

[0035] An updating module is used to perform multiple rounds of updates on the historical iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables to obtain multiple intermediate iteration independent variable groups, and determine the intermediate iteration independent variable group obtained by the last round of updating as the updated iteration independent variable group; wherein,

[0036] After each round of updating, it is determined whether the intermediate iterative independent variable group obtained in this round of updating is within the preset feasible domain. If the intermediate iterative independent variable group is within the preset feasible domain, the current round of updating is retained, and the next round of updating is performed based on the intermediate iterative independent variable group; if the intermediate iterative independent variable group is not within the preset feasible domain, the current round of updating is discarded, and the current round gradient value of the target independent variable corresponding to the current round of updating is updated to zero, and the next round of updating is performed.

[0037] Optionally, the device further comprises:

[0038] a calculation unit, configured to calculate, when there are maintenance parameters corresponding to the preset optimization algorithm, a current round update parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each of the target independent variables, after the optimization unit updates the historical iterative independent variable group according to the current round iterative independent variable group to obtain an updated iterative independent variable group;

[0039] An updating unit is used to update the current round parameter value corresponding to the maintenance parameter in the local storage space using the current round update parameter value corresponding to the maintenance parameter.

[0040] In a third aspect, an embodiment of the present application provides a storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the constrained optimization method of the objective function corresponding to the cement production process model described in the first aspect.

[0041] In a fourth aspect, an embodiment of the present application provides a constrained optimization device for an objective function corresponding to a cement production process model, the device comprising a storage medium; and one or more processors, the storage medium being coupled to the processor, the processor being configured to execute program instructions stored in the storage medium; when the program instructions are executed, the constrained optimization method for the objective function corresponding to the cement production process model described in the first aspect is executed.

[0042] By means of the above technical solution, the technical solution provided by this application has at least the following advantages:

[0043] The present application provides a constrained optimization method and device for an objective function corresponding to a cement production process model. After obtaining the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function, the present application can perform multiple rounds of iterative optimization on the objective function according to the initial independent variable group corresponding to the objective function and a preset optimization algorithm. After each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the optimization is within a preset feasible domain. If the current round of iterative independent variable group is within the preset feasible domain, it is determined whether the preset stop condition is met. If so, the iterative optimization is stopped. If not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stop condition is met. If so, the iterative optimization is stopped. If not, the next round of optimization is performed based on the updated iterative independent variable group. Since the preset optimization algorithm is specifically a gradient-based unconstrained optimization algorithm, in the present application, the constrained optimization of the objective function corresponding to the cement production process model is implemented based on the unconstrained optimization algorithm, so that the constrained optimization of the objective function corresponding to the cement production process model can be efficiently performed.

[0044] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0046] Figure 1 A flow chart of a constrained optimization method for a cement production process model corresponding to an objective function provided in an embodiment of the present application is shown;

[0047] Figure 2 A flow chart of a constraint optimization method corresponding to an objective function of another cement production process model provided in an embodiment of the present application is shown;

[0048] Figure 3 A block diagram showing a composition of a constrained optimization device for a cement production process model corresponding to an objective function provided by an embodiment of the present application is shown;

[0049] Figure 4 A block diagram of the composition of another constrained optimization device corresponding to an objective function of a cement production process model provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0050] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0051] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0052] The present application embodiment provides a method for optimizing the constraint of the objective function of a cement production process model. Figure 1 As shown, the method includes:

[0053] 101. Obtain the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function.

[0054] Among them, the objective function corresponding to the cement production process model is a pre-defined objective function corresponding to the function included in the cement production process model. The embodiment of the present application does not specifically limit the expression of the objective function corresponding to the cement production process model; wherein, the obtained objective function contains multiple target independent variables, and the initial independent variable group contains the initial set value corresponding to each target independent variable, and the initial set value corresponding to the target independent variable is pre-set by the staff based on work experience.

[0055] In an embodiment of the present application, it is first necessary to obtain the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function, so as to subsequently perform multiple rounds of iterative optimization on the objective function based on the initial independent variable group corresponding to the objective function.

[0056] 102. Perform multiple rounds of iterative optimization on the objective function based on the initial independent variable group and the preset optimization algorithm.

[0057] Among them, the preset optimization algorithm can be but is not limited to: stochastic gradient descent algorithm, variant algorithms of stochastic gradient descent algorithm, adaptive learning rate algorithm (such as AdaGrad algorithm, RMSProp algorithm, Adam algorithm), conjugate gradient algorithm, BFGS algorithm and other gradient-based unconstrained optimization algorithms.

[0058] In an embodiment of the present application, after obtaining the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function, the objective function can be subjected to multiple rounds of iterative optimization according to the initial independent variable group corresponding to the objective function and a preset optimization algorithm, wherein after each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the optimization is located within the preset feasible domain; if the current round of iterative independent variable group is located within the preset feasible domain, it is determined whether the preset stopping condition is met; if so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group; if the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stopping condition is met; if so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group. If it is reached, the iterative optimization is stopped. If it is not reached, the next round of optimization is performed based on the updated iterative independent variable group, wherein the preset feasible domain is used to determine whether the current round iteration values ​​corresponding to the various target independent variables contained in the current round iteration independent variable group obtained in the current round optimization meet the preset constrained optimization conditions, that is, when the current round iteration independent variable group obtained in the current round optimization is within the preset feasible domain, the current round iteration values ​​corresponding to the various target independent variables contained in the current round iteration independent variable group all meet the preset constrained optimization conditions; when the current round iteration independent variable group obtained in the current round optimization is not within the preset feasible domain, the current round iteration values ​​corresponding to one or more target independent variables contained in the current round iteration independent variable group do not meet the preset constrained optimization conditions; the historical iterative independent variable group is the current round iteration independent variable group or the updated iterative independent variable group corresponding to the previous round optimization.

[0059] The embodiment of the present application provides a constrained optimization method for an objective function corresponding to a cement production process model. The embodiment of the present application can perform multiple rounds of iterative optimization on the objective function according to the initial independent variable group corresponding to the objective function and a preset optimization algorithm after obtaining the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function. After each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the optimization is located within a preset feasible domain. If the current round of iterative independent variable group is located within the preset feasible domain, it is determined whether the preset stop condition is met. If so, the iterative optimization is stopped. If not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stop condition is met. If so, the iterative optimization is stopped. If not, the next round of optimization is performed based on the updated iterative independent variable group. Since the preset optimization algorithm is specifically a gradient-based unconstrained optimization algorithm, in the embodiment of the present application, the constrained optimization of the objective function corresponding to the cement production process model is implemented based on the unconstrained optimization algorithm, so that the constrained optimization of the objective function corresponding to the cement production process model can be efficiently performed.

[0060] To explain in more detail below, the present application embodiment provides another method for optimizing the constraint of the objective function of the cement production process model, as follows: Figure 2 As shown, the method includes:

[0061] 201. Obtain an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function.

[0062] Regarding step 201, obtaining the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function, please refer to Figure 1 The description of the corresponding parts of the embodiments of the present invention will not be repeated here.

[0063] 202. Perform multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm.

[0064] In an embodiment of the present application, after obtaining the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function, the objective function can be subjected to multiple rounds of iterative optimization according to the initial independent variable group corresponding to the objective function and a preset optimization algorithm, wherein after each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the optimization is located within the preset feasible domain; if the current round of iterative independent variable group is located within the preset feasible domain, it is determined whether the preset stopping condition is met; if so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group; if the current round of iterative independent variable group is within the preset feasible domain, it is determined whether the preset stopping condition is met; if so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group; If the variable group is not within the preset feasible domain, the historical iteration independent variable group is updated according to the current round iteration independent variable group to obtain the updated iteration independent variable group, and it is determined whether the preset stop condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the updated iteration independent variable group, wherein the preset feasible domain is used to determine whether the current round iteration values ​​corresponding to each target independent variable contained in the current round iteration independent variable group obtained in this round of optimization meet the preset constraint optimization conditions; the historical iteration independent variable group is the current round iteration independent variable group or the updated iteration independent variable group corresponding to the previous round of optimization.

[0065] Specifically, in this step, when there are maintenance parameters corresponding to the preset optimization algorithm, the objective function can be optimized for multiple rounds of iterations according to the initial independent variable group corresponding to the objective function and the preset optimization algorithm in the following manner:

[0066] For the first round of optimization: first, the initial setting value corresponding to each target independent variable is substituted into the objective function, and the current round gradient value corresponding to each target independent variable is calculated according to the objective function, that is, after the initial setting value corresponding to each target independent variable is substituted into the objective function, the partial derivative corresponding to each target independent variable is calculated according to the objective function, and then the calculated partial derivative corresponding to each target independent variable is determined as the current round gradient value corresponding to each target independent variable; secondly, the current round parameter value corresponding to the maintenance parameter is calculated according to the current round gradient value corresponding to each target independent variable, that is, the current round gradient value corresponding to each target independent variable and the preset multiple hyperparameter values ​​are substituted into the maintenance parameter calculation formula corresponding to the preset optimization algorithm, so as to calculate the current round parameter value corresponding to the maintenance parameter; thirdly, the current round parameter value corresponding to the maintenance parameter, the initial setting value corresponding to each target independent variable and the current round gradient value are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm, so as to calculate the current round iteration value corresponding to each target independent variable; finally, the current round iteration independent variable group is generated according to the current round iteration value corresponding to each target independent variable, and the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space;

[0067] For the N+1th round of optimization: first, obtain the historical iteration independent variable group, where the historical iteration independent variable group is the current round iteration independent variable group or the update iteration independent variable group corresponding to the previous round of optimization, and the historical iteration independent variable group contains the historical iteration value corresponding to each target independent variable; secondly, substitute the historical iteration value corresponding to each target independent variable into the objective function, and calculate the current round gradient value corresponding to each target independent variable according to the objective function, that is, after substituting the historical iteration value corresponding to each target independent variable into the objective function, calculate the partial derivative corresponding to each target independent variable according to the objective function, and then determine the calculated partial derivative corresponding to each target independent variable as the current round gradient value corresponding to each target independent variable; thirdly, calculate the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each target independent variable, where, for some preset optimization algorithms, the current round gradient value corresponding to each target independent variable and the preset The multiple hyperparameter values ​​that are set are substituted into the maintenance parameter calculation formula corresponding to the preset optimization algorithm, so as to calculate the current round parameter values ​​corresponding to the maintenance parameters. For some preset optimization algorithms, the N parameter values ​​corresponding to the maintenance parameters stored in the previous N rounds of optimization, the current round gradient value corresponding to each target independent variable, and the multiple hyperparameter values ​​that are preset are substituted into the maintenance parameter calculation formula corresponding to the preset optimization algorithm, so as to calculate the current round parameter values ​​corresponding to the maintenance parameters; then, the current round parameter values ​​corresponding to the maintenance parameters, the historical iteration values ​​corresponding to each target independent variable, and the current round gradient values ​​are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm, so as to calculate the current round iteration value corresponding to each target independent variable; finally, the current round iteration independent variable group is generated according to the current round iteration value corresponding to each target independent variable, and the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space; wherein N is a positive integer.

[0068] Specifically, in this step, when there is no maintenance parameter corresponding to the preset optimization algorithm, the objective function can be optimized for multiple rounds of iterations according to the initial independent variable group corresponding to the objective function and the preset optimization algorithm in the following manner:

[0069] For the first round of optimization: first, substitute the initial setting value corresponding to each target independent variable into the objective function, and calculate the current round gradient value corresponding to each target independent variable according to the objective function, that is, after substituting the initial setting value corresponding to each target independent variable into the objective function, calculate the partial derivative corresponding to each target independent variable according to the objective function, and then determine the calculated partial derivative corresponding to each target independent variable as the current round gradient value corresponding to each target independent variable; secondly, substitute the initial setting value and the current round gradient value corresponding to each target independent variable into the gradient descent calculation formula corresponding to the preset optimization algorithm, so as to calculate the current round iteration value corresponding to each target independent variable; finally, generate the current round iteration independent variable group according to the current round iteration value corresponding to each target independent variable, and store the current round iteration independent variable group in the local storage space;

[0070] For the N+1th round of optimization: first, obtain the historical iteration independent variable group, wherein the historical iteration independent variable group is the current round iteration independent variable group or the update iteration independent variable group corresponding to the previous round of optimization, and the historical iteration independent variable group contains the historical iteration value corresponding to each target independent variable; second, substitute the historical iteration value corresponding to each target independent variable into the objective function, and calculate the current round gradient value corresponding to each target independent variable according to the objective function, that is, after substituting the historical iteration value corresponding to each target independent variable into the objective function, calculate the partial derivative corresponding to each target independent variable according to the objective function, and then determine the calculated partial derivative corresponding to each target independent variable as the current round gradient value corresponding to each target independent variable; third, substitute the historical iteration value and the current round gradient value corresponding to each target independent variable into the gradient descent calculation formula corresponding to the preset optimization algorithm, so as to calculate the current round iteration value corresponding to each target independent variable; finally, generate the current round iteration independent variable group according to the current round iteration value corresponding to each target independent variable, and store the current round iteration independent variable group in the local storage space; wherein N is a positive integer.

[0071] Specifically, in this step, when the current round iteration independent variable group obtained by the current round optimization is not within the preset feasible domain, it is necessary to update the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group. The historical iteration independent variable group can be updated according to the current round iteration independent variable group in the following manner to obtain the updated iteration independent variable group:

[0072] First, the historical iteration independent variable group is updated for multiple rounds according to the current iteration value corresponding to each target independent variable contained in the current iteration independent variable group, so as to obtain multiple intermediate iteration independent variable groups, and then the intermediate iteration independent variable group obtained by the last round of update is determined as the updated iteration independent variable group, wherein the number of update rounds is the same as the number of target independent variables, and after each round of update, it is determined whether the intermediate iteration independent variable group obtained by the current round of update is within the preset feasible domain, if the intermediate iteration independent variable group is within the preset feasible domain, then the current round of update is retained, and the next round of update is performed based on the intermediate iteration independent variable group, if the intermediate iteration independent variable group is not within the preset feasible domain, then the current round of update is discarded, and the current round gradient value of the target independent variable corresponding to the current round of update is updated to zero, and then the next round of update is entered.

[0073] For example, in the first round of updates, the current round iteration value corresponding to the first target independent variable contained in the current round iteration independent variable group is used to update the historical iteration value corresponding to the first target independent variable contained in the historical iteration independent variable group (the arrangement order of multiple target independent variables contained in the current round iteration independent variable group is the same as the arrangement order of multiple target independent variables contained in the historical iteration independent variable group), thereby obtaining the first intermediate iteration independent variable group, and judging whether the first intermediate iteration independent variable group is within the preset feasible domain. If the first intermediate iteration independent variable group is within the preset feasible domain, the current round of updates is retained, and the next round of updates is performed based on the first intermediate iteration independent variable group. A round of update (i.e., in the second round of update, the current round iteration value corresponding to the second target independent variable contained in the current round iteration independent variable group is used to update the historical iteration value corresponding to the second target independent variable contained in the first intermediate iteration independent variable group). If the first intermediate iteration independent variable group is not within the preset feasible domain, the current round of update is abandoned, and the current round gradient value corresponding to the first target independent variable is updated to zero, and the next round of update is entered (i.e., in the second round of update, the current round iteration value corresponding to the second target independent variable contained in the current round iteration independent variable group is used to update the historical iteration value corresponding to the second target independent variable contained in the historical iteration independent variable group). Iteration value); perform a second round of updates, use the iteration value of this round corresponding to the second target independent variable contained in the iteration independent variable group of this round to update the historical iteration value corresponding to the second target independent variable contained in the first intermediate iteration independent variable group (or historical iteration independent variable group), thereby obtaining the second intermediate iteration independent variable group, and judging whether the second intermediate iteration independent variable group is within the preset feasible domain. If the second intermediate iteration independent variable group is within the preset feasible domain, retain this round of updates, and perform the next round of updates based on the second intermediate iteration independent variable group (that is, in the third round of updates, use the third target independent variable group contained in this round of iteration independent variable group). The current round iteration value corresponding to the independent variable updates the historical iteration value corresponding to the third target independent variable contained in the second intermediate iteration independent variable group). If the second intermediate iteration independent variable group is not within the preset feasible domain, the current round update is abandoned, and the current round gradient value corresponding to the second target independent variable is updated to zero, and the next round of update is entered [that is, in the third round of update, the current round iteration value corresponding to the third target independent variable contained in the current round iteration independent variable group is used to update the historical iteration value corresponding to the third target independent variable contained in the first intermediate iteration independent variable group (or historical iteration independent variable group)], and so on, until multiple rounds of updates are completed.

[0074] Further, in an embodiment of the present application, when there are maintenance parameters corresponding to a preset optimization algorithm, after each round of optimization, when the current round iteration independent variable group obtained by the current round optimization is not within the preset feasible domain, it is necessary to update the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group. Since, in the process of updating the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group, one or more current round gradient values ​​corresponding to the target independent variables will be updated, which will cause the current round parameter values ​​corresponding to the maintenance parameters calculated previously to be inaccurate. Therefore, it is necessary to update the current round parameter values ​​corresponding to the maintenance parameters, and the updating process is specifically as follows: first, according to the current round gradient value corresponding to each target independent variable, the current round update parameter value corresponding to the maintenance parameter is calculated, wherein the specific calculation process can refer to the description of the corresponding part of the previous step: calculating the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each target independent variable, and the embodiment of the present invention will not be repeated here; secondly, in the local storage space, the current round update parameter value corresponding to the maintenance parameter is updated using the current round update parameter value corresponding to the maintenance parameter.

[0075] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an embodiment of the present application also provides a storage medium, wherein the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the constrained optimization method of the objective function corresponding to the cement production process model described above.

[0076] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an embodiment of the present application also provides a constrained optimization device for an objective function corresponding to a cement production process model, the device comprising a storage medium; and one or more processors, the storage medium being coupled to the processor, the processor being configured to execute program instructions stored in the storage medium; when the program instructions are executed, the constrained optimization method for the objective function corresponding to the cement production process model described above is executed.

[0077] Furthermore, as a response to the above Figure 1 and Figure 2 In order to realize the method shown in the figure, another embodiment of the present application also provides a device for constraining optimization of the objective function corresponding to the cement production process model. This device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will no longer repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. This device is used to efficiently perform constrained optimization on the objective function corresponding to the cement production process model, specifically as follows Figure 3 As shown, the device comprises:

[0078] An acquisition unit 31 is used to acquire an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function includes a plurality of objective independent variables, and the initial independent variable group includes an initial setting value corresponding to each of the objective independent variables;

[0079] The optimization unit 32 is used to perform multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm; wherein,

[0080] After each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the current round of optimization is within the preset feasible domain. If the current round of iterative independent variable group is within the preset feasible domain, it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the updated iterative independent variable group, wherein the historical iterative independent variable group is the current round of iterative independent variable group or the updated iterative independent variable group corresponding to the previous round of optimization.

[0081] Further, such as Figure 4 As shown, the optimization unit 32 includes:

[0082] The first optimization module 321 is used for, when there are maintenance parameters corresponding to the preset optimization algorithm,

[0083] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the current round parameter value corresponding to the maintenance parameter is calculated according to the current round gradient value corresponding to each of the target independent variables; the current round parameter value corresponding to the maintenance parameter, the initial setting value corresponding to each of the target independent variables and the current round gradient value are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space;

[0084] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; calculate the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each of the target independent variables; substitute the current round parameter value corresponding to the maintenance parameter, the historical iteration value corresponding to each of the target independent variables and the current round gradient value into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate the current round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter in the local storage space; wherein N is a positive integer.

[0085] Further, such as Figure 4 As shown, the optimization unit 32 includes:

[0086] The second optimization module 322 is used for, when there is no maintenance parameter corresponding to the preset optimization algorithm,

[0087] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the initial setting value and the current round gradient value corresponding to each of the target independent variables are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is stored in the local storage space;

[0088] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; substitute the historical iteration values ​​and current round gradient values ​​corresponding to each of the target independent variables into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate this round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group in the local storage space; wherein N is a positive integer.

[0089] Further, such as Figure 4 As shown, the optimization unit 32 includes:

[0090] The updating module 323 is used to perform multiple rounds of updates on the historical iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables to obtain multiple intermediate iteration independent variable groups, and determine the intermediate iteration independent variable group obtained by the last round of updating as the updated iteration independent variable group; wherein,

[0091] After each round of updating, it is determined whether the intermediate iterative independent variable group obtained in this round of updating is within the preset feasible domain. If the intermediate iterative independent variable group is within the preset feasible domain, the current round of updating is retained, and the next round of updating is performed based on the intermediate iterative independent variable group; if the intermediate iterative independent variable group is not within the preset feasible domain, the current round of updating is discarded, and the current round gradient value of the target independent variable corresponding to the current round of updating is updated to zero, and the next round of updating is performed.

[0092] Further, such as Figure 4 As shown, the device also includes:

[0093] The calculation unit 33 is used for, when there are maintenance parameters corresponding to the preset optimization algorithm, calculating the current round update parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each target independent variable after the optimization unit 32 updates the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group;

[0094] The updating unit 34 is configured to update the current round parameter value corresponding to the maintenance parameter in the local storage space using the current round update parameter value corresponding to the maintenance parameter.

[0095] The embodiment of the present application provides a constrained optimization method and device for an objective function corresponding to a cement production process model. The embodiment of the present application can perform multiple rounds of iterative optimization on the objective function according to the initial independent variable group corresponding to the objective function and a preset optimization algorithm after obtaining the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function. After each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the optimization is located within a preset feasible domain. If the current round of iterative independent variable group is located within the preset feasible domain, it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped. If not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped. If not, the next round of optimization is performed based on the updated iterative independent variable group. Since the preset optimization algorithm is specifically a gradient-based unconstrained optimization algorithm, in the embodiment of the present application, the constrained optimization of the objective function corresponding to the cement production process model is implemented based on the unconstrained optimization algorithm, so that the constrained optimization of the objective function corresponding to the cement production process model can be efficiently performed.

[0096] The constraint optimization device corresponding to the objective function of the cement production process model includes a processor and a memory. The above-mentioned acquisition unit and optimization unit are stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0097] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the objective function corresponding to the cement production process model can be efficiently constrained and optimized by adjusting the kernel parameters.

[0098] An embodiment of the present application provides a storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the constrained optimization method corresponding to the objective function of the cement production process model described above.

[0099] The storage medium may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0100] An embodiment of the present application also provides a constrained optimization device for an objective function corresponding to a cement production process model, the device comprising a storage medium; and one or more processors, the storage medium being coupled to the processor, the processor being configured to execute program instructions stored in the storage medium; and the program instructions executing the above-mentioned constrained optimization method for an objective function corresponding to a cement production process model.

[0101] The embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented:

[0102] Obtaining an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function includes a plurality of objective independent variables, and the initial independent variable group includes an initial set value corresponding to each of the objective independent variables;

[0103] The objective function is optimized for multiple rounds of iterations according to the initial independent variable group and the preset optimization algorithm; wherein,

[0104] After each round of optimization, it is determined whether the current round of iterative independent variable group obtained by the current round of optimization is within the preset feasible domain. If the current round of iterative independent variable group is within the preset feasible domain, it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the updated iterative independent variable group, wherein the historical iterative independent variable group is the current round of iterative independent variable group or the updated iterative independent variable group corresponding to the previous round of optimization.

[0105] Further, when there are maintenance parameters corresponding to the preset optimization algorithm, performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm includes:

[0106] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the current round parameter value corresponding to the maintenance parameter is calculated according to the current round gradient value corresponding to each of the target independent variables; the current round parameter value corresponding to the maintenance parameter, the initial setting value corresponding to each of the target independent variables and the current round gradient value are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space;

[0107] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; calculate the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each of the target independent variables; substitute the current round parameter value corresponding to the maintenance parameter, the historical iteration value corresponding to each of the target independent variables and the current round gradient value into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate the current round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter in the local storage space; wherein N is a positive integer.

[0108] Further, when there is no maintenance parameter corresponding to the preset optimization algorithm, performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm includes:

[0109] For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the initial setting value and the current round gradient value corresponding to each of the target independent variables are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is stored in the local storage space;

[0110] For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; substitute the historical iteration values ​​and current round gradient values ​​corresponding to each of the target independent variables into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate this round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group in the local storage space; wherein N is a positive integer.

[0111] Further, the updating of the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group includes:

[0112] The historical iteration independent variable group is updated multiple times according to the current iteration value corresponding to each target independent variable to obtain multiple intermediate iteration independent variable groups, and the intermediate iteration independent variable group obtained by the last round of updating is determined as the updated iteration independent variable group; wherein,

[0113] After each round of updating, it is determined whether the intermediate iterative independent variable group obtained in this round of updating is within the preset feasible domain. If the intermediate iterative independent variable group is within the preset feasible domain, the current round of updating is retained, and the next round of updating is performed based on the intermediate iterative independent variable group; if the intermediate iterative independent variable group is not within the preset feasible domain, the current round of updating is discarded, and the current round gradient value of the target independent variable corresponding to the current round of updating is updated to zero, and the next round of updating is performed.

[0114] Further, when there are maintenance parameters corresponding to the preset optimization algorithm, after updating the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group, the method further includes:

[0115] Calculate the current round update parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each target independent variable;

[0116] In the local storage space, the current round update parameter value corresponding to the maintenance parameter is updated using the current round update parameter value corresponding to the maintenance parameter.

[0117] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing program code that initializes the following method steps: obtaining an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function includes multiple target independent variables, and the initial independent variable group includes an initial set value corresponding to each of the target independent variables; performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm; wherein, after each round of optimization, determining whether the iterative independent variable group obtained in the current round of optimization is within a preset feasible domain, and if the iterative independent variable group is within a preset feasible domain, determining whether the iterative independent variable group is within a preset feasible domain; If the preset stopping condition is within the preset feasible domain, it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the current round of iterative independent variable group. If the current round of iterative independent variable group is not within the preset feasible domain, the historical iterative independent variable group is updated according to the current round of iterative independent variable group to obtain an updated iterative independent variable group, and it is determined whether the preset stopping condition is met. If so, the iterative optimization is stopped; if not, the next round of optimization is performed based on the updated iterative independent variable group, wherein the historical iterative independent variable group is the current round of iterative independent variable group or the updated iterative independent variable group corresponding to the previous round of optimization.

[0118] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0119] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0122] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0123] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0124] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0125] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0126] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0127] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A constrained optimization method for the objective function of a cement production process model. It is characterized in that The method comprises: Obtaining an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function includes a plurality of objective independent variables, and the initial independent variable group includes an initial set value corresponding to each of the objective independent variables; The objective function is optimized for multiple rounds of iterations according to the initial independent variable group and the preset optimization algorithm, wherein the preset optimization algorithm is a gradient-based unconstrained optimization algorithm; wherein, After each round of optimization, it is determined whether the current round of iteration independent variable group obtained in the current round of optimization is within the preset feasible domain. If the current round of iteration independent variable group is within the preset feasible domain, it is determined whether the preset stop condition is met. If so, iterative optimization is stopped. If not, the next round of optimization is performed based on the current round of iteration independent variable group. If the current round of iteration independent variable group is not within the preset feasible domain, the historical iteration independent variable group is updated according to the current round of iteration independent variable group to obtain an updated iteration independent variable group, and it is determined whether the preset stop condition is met. If so, iterative optimization is stopped. If not, the next round of optimization is performed based on the updated iteration independent variable group, wherein the preset feasible domain is used to determine whether the current round iteration values ​​corresponding to the various target independent variables contained in the current round of iteration independent variable group obtained in the current round of optimization meet the preset constraint optimization conditions. The historical iteration independent variable group is the current round of iteration independent variable group or the updated iteration independent variable group corresponding to the previous round of optimization. The updating of the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group includes: The historical iteration independent variable group is updated multiple times according to the current iteration value corresponding to each target independent variable to obtain multiple intermediate iteration independent variable groups, and the intermediate iteration independent variable group obtained by the last round of update is determined as the updated iteration independent variable group; wherein, After each round of updating, it is determined whether the intermediate iterative independent variable group obtained in this round of updating is within the preset feasible domain. If the intermediate iterative independent variable group is within the preset feasible domain, the current round of updating is retained, and the next round of updating is performed based on the intermediate iterative independent variable group; if the intermediate iterative independent variable group is not within the preset feasible domain, the current round of updating is discarded, and the current round gradient value of the target independent variable corresponding to the current round of updating is updated to zero, and the next round of updating is performed.

2. The method according to claim 1, It is characterized in that When there are maintenance parameters corresponding to the preset optimization algorithm, performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm includes: For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the current round parameter value corresponding to the maintenance parameter is calculated according to the current round gradient value corresponding to each of the target independent variables; the current round parameter value corresponding to the maintenance parameter, the initial setting value corresponding to each of the target independent variables and the current round gradient value are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space; For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; calculate the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each of the target independent variables; substitute the current round parameter value corresponding to the maintenance parameter, the historical iteration value corresponding to each of the target independent variables and the current round gradient value into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate the current round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter in the local storage space; wherein N is a positive integer.

3. The method according to claim 1, It is characterized in that When there is no maintenance parameter corresponding to the preset optimization algorithm, performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and the preset optimization algorithm includes: For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the initial setting value and the current round gradient value corresponding to each of the target independent variables are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is stored in the local storage space; For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; substitute the historical iteration values ​​and current round gradient values ​​corresponding to each of the target independent variables into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate this round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group in the local storage space; wherein N is a positive integer.

4. The method according to claim 2 or 3, It is characterized in that When there are maintenance parameters corresponding to the preset optimization algorithm, after updating the historical iteration independent variable group according to the current round iteration independent variable group to obtain the updated iteration independent variable group, the method further includes: Calculate the current round update parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each target independent variable; In the local storage space, the current round update parameter value corresponding to the maintenance parameter is updated using the current round update parameter value corresponding to the maintenance parameter.

5. A constrained optimization device corresponding to the objective function of a cement production process model, It is characterized in that The device adopts the constraint optimization method corresponding to the objective function of the cement production process model according to any one of claims 1 to 4, and the device comprises: An acquisition unit, used for acquiring an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, wherein the objective function includes a plurality of objective independent variables, and the initial independent variable group includes an initial setting value corresponding to each of the objective independent variables; An optimization unit, used for performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm, wherein the preset optimization algorithm is a gradient-based unconstrained optimization algorithm; wherein, After each round of optimization, it is determined whether the current round of iteration independent variable group obtained in the current round of optimization is within the preset feasible domain. If the current round of iteration independent variable group is within the preset feasible domain, it is determined whether the preset stop condition is met. If so, iterative optimization is stopped. If not, the next round of optimization is performed based on the current round of iteration independent variable group. If the current round of iteration independent variable group is not within the preset feasible domain, the historical iteration independent variable group is updated according to the current round of iteration independent variable group to obtain an updated iteration independent variable group, and it is determined whether the preset stop condition is met. If so, iterative optimization is stopped. If not, the next round of optimization is performed based on the updated iteration independent variable group, wherein the preset feasible domain is used to determine whether the current round iteration values ​​corresponding to the various target independent variables contained in the current round of iteration independent variable group obtained in the current round of optimization meet the preset constraint optimization conditions. The historical iteration independent variable group is the current round of iteration independent variable group or the updated iteration independent variable group corresponding to the previous round of optimization. The optimization unit comprises: An updating module is used to perform multiple rounds of updates on the historical iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables to obtain multiple intermediate iteration independent variable groups, and determine the intermediate iteration independent variable group obtained by the last round of updating as the updated iteration independent variable group; wherein, After each round of updating, it is determined whether the intermediate iterative independent variable group obtained in this round of updating is within the preset feasible domain. If the intermediate iterative independent variable group is within the preset feasible domain, the current round of updating is retained, and the next round of updating is performed based on the intermediate iterative independent variable group; if the intermediate iterative independent variable group is not within the preset feasible domain, the current round of updating is discarded, and the current round gradient value of the target independent variable corresponding to the current round of updating is updated to zero, and the next round of updating is performed.

6. The device according to claim 5, It is characterized in that The optimization unit comprises: The first optimization module is used for, when there are maintenance parameters corresponding to the preset optimization algorithm, For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the current round parameter value corresponding to the maintenance parameter is calculated according to the current round gradient value corresponding to each of the target independent variables; the current round parameter value corresponding to the maintenance parameter, the initial setting value corresponding to each of the target independent variables and the current round gradient value are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter are stored in the local storage space; For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; calculate the current round parameter value corresponding to the maintenance parameter according to the current round gradient value corresponding to each of the target independent variables; substitute the current round parameter value corresponding to the maintenance parameter, the historical iteration value corresponding to each of the target independent variables and the current round gradient value into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate the current round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group and the current round parameter value corresponding to the maintenance parameter in the local storage space; wherein N is a positive integer.

7. The device according to claim 5, It is characterized in that The optimization unit comprises: The second optimization module is used for, when there is no maintenance parameter corresponding to the preset optimization algorithm, For the first round of optimization: the initial setting value corresponding to each of the target independent variables is substituted into the target function, and the current round gradient value corresponding to each of the target independent variables is calculated according to the target function; the initial setting value and the current round gradient value corresponding to each of the target independent variables are substituted into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is generated according to the current round iteration value corresponding to each of the target independent variables; the current round iteration independent variable group is stored in the local storage space; For the N+1th round of optimization: obtain a historical iteration independent variable group, which includes historical iteration values ​​corresponding to each of the target independent variables; substitute the historical iteration values ​​corresponding to each of the target independent variables into the objective function, and calculate the current round gradient value corresponding to each of the target independent variables according to the objective function; substitute the historical iteration values ​​and current round gradient values ​​corresponding to each of the target independent variables into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration value corresponding to each of the target independent variables; generate this round iteration independent variable group according to the current round iteration value corresponding to each of the target independent variables; store the current round iteration independent variable group in the local storage space; wherein N is a positive integer.

8. A storage medium, It is characterized in that The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the constrained optimization method corresponding to the objective function of the cement production process model described in any one of claims 1 to 4.

9. A constrained optimization device corresponding to the objective function of a cement production process model, It is characterized in that The device includes a storage medium; and one or more processors, the storage medium is coupled to the processor, and the processor is configured to execute program instructions stored in the storage medium; when the program instructions are executed, the constrained optimization method corresponding to the objective function of the cement production process model described in any one of claims 1 to 4 is executed.