CN113449433A

CN113449433A - Constraint optimization method and device for objective function corresponding to cement production process model

Info

Publication number: CN113449433A
Application number: CN202110808431.0A
Authority: CN
Inventors: 张翼; 夏凌风; 蒙景怡; 李响; 郭珍妮; 赵博雅; 赵峙杰; 邱林; 郑明迪; 范金磊; 孙盈盈; 贺梦蛟; 张浩华; 秦宪明
Original assignee: Zhongcun Big Data Technology Co ltd
Current assignee: Zhongcun Big Data Technology Co ltd
Priority date: 2021-07-16
Filing date: 2021-07-16
Publication date: 2021-09-28

Abstract

The application discloses a constraint optimization method and device for a cement production process model corresponding to an objective function, 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 comprises a plurality of objective independent variables, and the initial independent variable group comprises initial set values corresponding to each objective independent variable; and performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm.

Description

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

Technical Field

The application relates to the technical field of cement production, in particular to a constraint optimization method and device for a cement production process model corresponding to an objective function.

Background

In the field of cement production technology, cement production process models are used to simulate preheaters and rotary kilns. After the measured data of the quality, components and the like of raw materials and coal are input into the cement production process model, the cement production process model can output information of materials, flue gas flow, flue gas temperature, flue gas components and the like at the outlet of each device, thereby providing data support for the actual production of cement.

In order to ensure the accuracy of the output information of the cement production process model, an objective function corresponding to a function contained in the cement production process model needs to be defined, and the defined objective function is constrained and optimized, so that the cement production process model is checked. Therefore, how to efficiently perform constraint optimization on the objective function corresponding to the cement production process model is crucial.

Disclosure of Invention

The embodiment of the application provides a constraint optimization method and device for an objective function corresponding to a cement production process model, and mainly aims to efficiently carry out constraint optimization on the objective function corresponding to the cement production process model.

In order to solve the above technical problem, an embodiment of the present application provides the following technical solutions:

in a first aspect, the present application provides a constrained optimization method for an objective function corresponding to a cement production process model, the method comprising:

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 comprises a plurality of objective independent variables, and the initial independent variable group comprises initial set values corresponding to each objective independent variable;

performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm; wherein the content of the first and second substances,

after each round of optimization, judging whether a current round of iteration independent variable group obtained by the current round of optimization is located in a preset feasible region, if so, judging whether a preset stopping condition is reached, if so, stopping the iteration optimization, and if not, performing next round of optimization based on the current round of iteration independent variable group; if the iteration independent variable group of the current round is not located in the preset feasible region, updating a historical iteration independent variable group according to the iteration independent variable group of the current round to obtain an updated iteration independent variable group, judging whether the preset stopping condition is reached, if so, stopping iteration optimization, and if not, performing next round of optimization based on the updated iteration independent variable group, wherein the historical iteration independent variable group is the iteration independent variable group of the current round corresponding to the previous round of optimization or the updated iteration independent variable group.

Optionally, when there is a 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, including:

for the first round of optimization: substituting the initial set value corresponding to each target independent variable into the target function, and calculating the gradient value of the current round corresponding to each target independent variable according to the target function; calculating the local round parameter value corresponding to the maintenance parameter according to the local round gradient value corresponding to each target independent variable; substituting the parameter values of the current round corresponding to the maintenance parameters, the initial set value corresponding to each target independent variable and the gradient value of the current round into a gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the iteration value of the current round corresponding to each target independent variable; generating a current iteration independent variable group according to the current iteration value corresponding to each target independent variable; storing the iteration independent variable group of the current round and the parameter value of the current round corresponding to the maintenance parameter into a local storage space;

for the N +1 th round of optimization: acquiring a historical iteration independent variable group, wherein the historical iteration independent variable group comprises a historical iteration value corresponding to each target independent variable; substituting the historical iteration value corresponding to each target independent variable into the target function, and calculating the gradient value of the current round corresponding to each target independent variable according to the target function; calculating the local round parameter value corresponding to the maintenance parameter according to the local round gradient value corresponding to each target independent variable; substituting the current round parameter values corresponding to the maintenance parameters, the historical iteration values corresponding to the target independent variables and the current round gradient values into a gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the current round iteration values corresponding to the target independent variables; generating a current iteration independent variable group according to the current iteration value corresponding to each target independent variable; storing the iteration independent variable group of the current round and the parameter value of the current round corresponding to the maintenance parameter into the local storage space; wherein N is a positive integer.

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, including:

for the first round of optimization: substituting the initial set value corresponding to each target independent variable into the target function, and calculating the gradient value of the current round corresponding to each target independent variable according to the target function; substituting the initial set value and the gradient value of the current round corresponding to each target independent variable into a gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the iteration value of the current round corresponding to each target independent variable; generating a current iteration independent variable group according to the current iteration value corresponding to each target independent variable; storing the iteration independent variable group of the current round into a local storage space;

for the N +1 th round of optimization: acquiring a historical iteration independent variable group, wherein the historical iteration independent variable group comprises a historical iteration value corresponding to each target independent variable; substituting the historical iteration value corresponding to each target independent variable into the target function, and calculating the gradient value of the current round corresponding to each target independent variable according to the target function; substituting the historical iteration value and the gradient value of the current round corresponding to each target independent variable into the gradient descent calculation formula corresponding to the preset optimization algorithm to calculate the iteration value of the current round corresponding to each target independent variable; generating a current iteration independent variable group according to the current iteration value corresponding to each target independent variable; storing the iteration independent variable group of the current round into the local storage space; wherein N is a positive integer.

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

performing multiple rounds of updating on the historical iteration independent variable group according to the iteration value of the current round corresponding to each target independent variable to obtain a plurality of intermediate iteration independent variable groups, and determining the intermediate iteration independent variable group obtained by the last round of updating as the updated iteration independent variable group; wherein the content of the first and second substances,

after each round of updating, judging whether an intermediate iteration independent variable group obtained by the current round of updating is located in the preset feasible region, if so, keeping the current round of updating, and performing the next round of updating based on the intermediate iteration independent variable group; and if the intermediate iteration independent variable group is not located in the preset feasible region, abandoning the updating of the current round, updating the gradient value of the current round of the target independent variable corresponding to the updating of the current round to zero, and entering the next round of updating.

Optionally, when there is a maintenance parameter corresponding to the preset optimization algorithm, after the historical iteration independent variable group is updated according to the iteration independent variable group in the current round to obtain an updated iteration independent variable group, the method further includes:

calculating a local update parameter value corresponding to the maintenance parameter according to the local gradient value corresponding to each target independent variable;

and updating the current round parameter values corresponding to the maintenance parameters by using the current round updating parameter values corresponding to the maintenance parameters in the local storage space.

In a second aspect, the present application further provides a constraint optimization apparatus for a cement production process model corresponding to an objective function, the apparatus comprising:

the system comprises an acquisition unit, a calculation unit and a processing unit, wherein the acquisition unit is used for acquiring an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, the objective function comprises a plurality of objective independent variables, and the initial independent variable group comprises initial set values corresponding to each objective independent variable;

the optimization unit is used for carrying out multi-round iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm; wherein the content of the first and second substances,

Optionally, the optimizing unit includes:

a first optimization module, configured to, when there is a maintenance parameter corresponding to the preset optimization algorithm,

Optionally, the optimizing unit includes:

a second optimization module, configured to, when there is no maintenance parameter corresponding to the preset optimization algorithm,

Optionally, the optimizing unit includes:

the updating module is used for performing multiple rounds of updating on the historical iteration independent variable group according to the iteration value corresponding to each target independent variable so as to obtain a plurality of intermediate iteration independent variable groups, and determining the intermediate iteration independent variable group obtained by the last round of updating as the updated iteration independent variable group; wherein the content of the first and second substances,

Optionally, the apparatus further comprises:

a calculating unit, configured to, when there is a maintenance parameter corresponding to the preset optimization algorithm, update, at the optimizing unit, a historical iteration independent variable group according to the iteration independent variable group in the current round to obtain an updated iteration independent variable group, and then calculate, according to a gradient value in the current round corresponding to each target independent variable, an update parameter value in the current round corresponding to the maintenance parameter;

and the updating unit is used for updating the current round of parameter values corresponding to the maintenance parameters by using the current round of updating parameter values corresponding to the maintenance parameters in the local storage space.

In a third aspect, an embodiment of the present application provides a storage medium, where the storage medium includes a stored program, where when the program runs, the apparatus in which the storage medium is located is controlled to execute the constraint optimization method for the cement production process model corresponding to the objective function according to the first aspect.

In a fourth aspect, an embodiment of the present application provides a constraint optimization apparatus for a cement production process model corresponding to an objective function, where the apparatus includes a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; and when the program instructions are operated, executing the constraint optimization method of the cement production process model corresponding to the objective function in the first aspect.

By means of the technical scheme, the technical scheme provided by the application at least has the following advantages:

the method and the device can perform multi-round iterative optimization on the target function according to the initial independent variable group corresponding to the target function and a preset optimization algorithm after obtaining the target function corresponding to the cement production process model and the initial independent variable group corresponding to the target function, wherein after each round of optimization, whether the iteration independent variable group obtained by the round of optimization is located in a preset feasible region is judged, if the iteration independent variable group is located in the preset feasible region, whether a preset stopping condition is reached is judged, if so, the iteration optimization is stopped, and if not, the next round of optimization is performed based on the iteration independent variable group; and if the iteration independent variable group of the current round is not located in the preset feasible region, updating the historical iteration independent variable group according to the iteration independent variable group of the current round, so as to obtain an updated iteration independent variable group, judging whether a preset stop condition is met, if so, stopping iteration optimization, and if not, performing next round of optimization based on the updated iteration independent variable group. Since the preset optimization algorithm is specifically an unconstrained optimization algorithm based on the gradient, the unconstrained optimization algorithm is used for realizing constrained optimization of the objective function corresponding to the cement production process model, so that the objective function corresponding to the cement production process model can be efficiently constrained and optimized.

The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.

Drawings

The above and other objects, features and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present application are illustrated by way of example and not by way of limitation in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:

FIG. 1 is a flow chart of a method for constrained optimization of an objective function corresponding to a cement production process model according to an embodiment of the present disclosure;

FIG. 2 is a flow chart of a constraint optimization method for an objective function corresponding to another cement production process model provided in the embodiment of the present application;

FIG. 3 is a block diagram illustrating a constraint optimization apparatus for an objective function corresponding to a cement production process model according to an embodiment of the present disclosure;

fig. 4 is a block diagram illustrating a constraint optimization apparatus for an objective function corresponding to another cement production process model provided in an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which this application belongs.

The embodiment of the application provides a constraint optimization method for a cement production process model corresponding to an objective function, as shown in fig. 1, the method comprises the following steps:

101. and acquiring an objective function corresponding to the cement production process model and an initial independent variable group corresponding to the objective function.

The target function corresponding to the cement production process model is predefined, the cement production process model comprises the target function corresponding to the function, and the expression of the target function corresponding to the cement production process model is not specifically limited in the embodiment of the application; the obtained target function comprises a plurality of target independent variables, the initial independent variable group comprises an initial set value corresponding to each target independent variable, and the initial set value corresponding to the target independent variable is preset by a worker according to work experience.

In the embodiment of the application, an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function need to be obtained first, so that multiple rounds of iterative optimization are performed on the objective function based on the initial independent variable group corresponding to the objective function.

102. And performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm.

The preset optimization algorithm may be, but is not limited to: a random gradient descent algorithm, a variant algorithm of the random gradient descent algorithm, an adaptive learning rate algorithm (such as an AdaGrad algorithm, a RMSProp algorithm, an Adam algorithm), a conjugate gradient algorithm, a BFGS algorithm, and other gradient-based unconstrained optimization algorithms.

In the embodiment of the application, after obtaining the target function corresponding to the cement production process model and the initial independent variable group corresponding to the target function, performing multiple rounds of iterative optimization on the target function according to the initial independent variable group corresponding to the target function and a preset optimization algorithm, wherein after each round of optimization, judging whether the iteration independent variable group obtained by the round of optimization is located in a preset feasible region, if the iteration independent variable group is located in the preset feasible region, judging whether a preset stop condition is reached, if so, stopping the iterative optimization, and if not, performing the next round of optimization based on the iteration independent variable group; if the iteration independent variable group of the current round is not positioned in the preset feasible region, updating the historical iteration independent variable group according to the iteration independent variable group of the current round, thereby obtaining an updated iteration independent variable group, judging whether a preset stop condition is reached or not, if so, stopping the iteration optimization, and if not, performing next round of optimization based on the updated iteration independent variable group, wherein the preset feasible region is used for judging whether the iteration value of the current round corresponding to each target independent variable contained in the iteration independent variable group of the current round obtained by the current round of optimization meets a preset constraint optimization condition or not, namely when the iteration independent variable group of the current round obtained by the current round of optimization is positioned in the preset feasible region, the iteration value of the current round corresponding to each target independent variable contained in the iteration independent variable group of the current round meets the preset constraint optimization condition, and when the iteration independent variable group of the current round obtained by the current round of optimization is not positioned in the preset feasible region, the iteration value of the current round corresponding to one or more target independent variables contained in the iteration independent variable group of the current round does not meet the preset constraint optimization condition; the historical iteration independent variable group is the iteration independent variable group of the current round corresponding to the previous round of optimization or the updated iteration independent variable group.

The embodiment of the application provides a constraint optimization method of a target function corresponding to a cement production process model, and the method can perform multi-round iterative optimization on the target function according to an initial independent variable group corresponding to the target function and a preset optimization algorithm after obtaining the target function corresponding to the cement production process model and the initial independent variable group corresponding to the target function, wherein after each round of optimization, whether the iteration independent variable group obtained by the round of optimization is located in a preset feasible region or not is judged, if the iteration independent variable group is located in the preset feasible region, whether a preset stop condition is reached or not is judged, if so, the iteration optimization is stopped, and if not, the next round of optimization is performed based on the iteration independent variable group; and if the iteration independent variable group of the current round is not located in the preset feasible region, updating the historical iteration independent variable group according to the iteration independent variable group of the current round, so as to obtain an updated iteration independent variable group, judging whether a preset stop condition is met, if so, stopping iteration optimization, and if not, performing next round of optimization based on the updated iteration independent variable group. Since the preset optimization algorithm is specifically an unconstrained optimization algorithm based on a gradient, in the embodiment of the application, the unconstrained optimization algorithm is used for realizing constrained optimization of the objective function corresponding to the cement production process model, so that the constrained optimization of the objective function corresponding to the cement production process model can be efficiently performed.

For the following description in more detail, an embodiment of the present application provides another method for constrained optimization of an objective function corresponding to a cement production process model, specifically as shown in fig. 2, where the method includes:

201. and acquiring an objective function corresponding to the cement production process model and an initial independent variable group corresponding to the objective function.

In step 201, the objective function corresponding to the cement production process model and the initial independent variable group corresponding to the objective function may be obtained by referring to the description of the corresponding part in fig. 1, and details of the embodiment of the present invention will not be repeated here.

202. And performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm.

In the embodiment of the application, after obtaining the target function corresponding to the cement production process model and the initial independent variable group corresponding to the target function, performing multiple rounds of iterative optimization on the target function according to the initial independent variable group corresponding to the target function and a preset optimization algorithm, wherein after each round of optimization, judging whether the iteration independent variable group obtained by the round of optimization is located in a preset feasible region, if the iteration independent variable group is located in the preset feasible region, judging whether a preset stop condition is reached, if so, stopping the iterative optimization, and if not, performing the next round of optimization based on the iteration independent variable group; if the iteration independent variable group of the current round is not located in the preset feasible region, updating the historical iteration independent variable group according to the iteration independent variable group of the current round, so as to obtain an updated iteration independent variable group, judging whether a preset stop condition is reached, if so, stopping iteration optimization, and if not, performing next round of optimization based on the updated iteration independent variable group, wherein the preset feasible region is used for judging whether the iteration value of the current round corresponding to each target independent variable contained in the iteration independent variable group of the current round obtained by the current round of optimization meets a preset constraint optimization condition; the historical iteration independent variable group is the iteration independent variable group of the current round corresponding to the previous round of optimization or the updated iteration independent variable group.

Specifically, in this step, when there is a maintenance parameter corresponding to the preset optimization algorithm, the objective function may be iteratively optimized for multiple rounds according to the initial independent variable group corresponding to the objective function and the preset optimization algorithm in the following manner:

for the first round of optimization: firstly, substituting an initial set value corresponding to each target independent variable into a target function, and calculating a gradient value of a current round corresponding to each target independent variable according to the target function, namely calculating a partial derivative corresponding to each target independent variable according to the target function after substituting the initial set value corresponding to each target independent variable into the target function, and determining the partial derivative corresponding to each target independent variable obtained by calculation as the gradient value of the current round corresponding to each target independent variable; secondly, calculating the local round parameter values corresponding to the maintenance parameters according to the local round gradient values corresponding to the target independent variables, namely substituting the local round gradient values corresponding to the target independent variables and a plurality of preset super parameter values into a maintenance parameter calculation formula corresponding to a preset optimization algorithm, so as to calculate the local round parameter values corresponding to the maintenance parameters; thirdly, substituting the parameters of the current round corresponding to the maintenance parameters, the initial set value corresponding to each target independent variable and the gradient value of the current round into a gradient descent calculation formula corresponding to a preset optimization algorithm, and calculating the iteration value of the current round corresponding to each target independent variable; finally, generating a local iteration independent variable group according to the local iteration value corresponding to each target independent variable, and storing the local iteration independent variable group and the local parameter value corresponding to the maintenance parameter into a local storage space;

for the N +1 th round of optimization: firstly, obtaining a historical iteration independent variable group, wherein the historical iteration independent variable group is a current iteration independent variable group corresponding to previous optimization or an updated iteration independent variable group, and the historical iteration independent variable group comprises a historical iteration value corresponding to each target independent variable; secondly, substituting the historical iteration value corresponding to each target independent variable into the target function, and calculating the gradient value of the current round corresponding to each target independent variable according to the target function, namely calculating the partial derivative corresponding to each target independent variable according to the target function after substituting the historical iteration value corresponding to each target independent variable into the target function, and determining the partial derivative corresponding to each target independent variable obtained by calculation as the gradient value of the current round corresponding to each target independent variable; thirdly, calculating the parameters of the current round corresponding to the maintenance parameters according to the gradient values of the current round corresponding to each target independent variable, wherein for part of preset optimization algorithms, the gradient values of the current round corresponding to each target independent variable and a plurality of preset super parameter values are substituted into a maintenance parameter calculation formula corresponding to the preset optimization algorithms, so as to calculate the parameters of the current round corresponding to the maintenance parameters, and for part of preset optimization algorithms, the gradient values of the current round corresponding to the maintenance parameters, the gradient values of the current round corresponding to each target independent variable and the plurality of preset super parameter values stored in the previous N-round optimization are substituted into a maintenance parameter calculation formula corresponding to the preset optimization algorithms, so as to calculate the parameters of the current round corresponding to the maintenance parameters; then, substituting the current round parameter value corresponding to the maintenance parameter, the historical iteration value corresponding to each target independent variable and the current round gradient value into a gradient descent calculation formula corresponding to a preset optimization algorithm, and calculating the current round iteration value corresponding to each target independent variable; finally, generating a local iteration independent variable group according to the local iteration value corresponding to each target independent variable, and storing the local iteration independent variable group and the local parameter value corresponding to the maintenance parameter into a local storage space; wherein N is a positive integer.

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

for the first round of optimization: firstly, substituting an initial set value corresponding to each target independent variable into a target function, and calculating a gradient value of a current round corresponding to each target independent variable according to the target function, namely calculating a partial derivative corresponding to each target independent variable according to the target function after substituting the initial set value corresponding to each target independent variable into the target function, and determining the partial derivative corresponding to each target independent variable obtained by calculation as the gradient value of the current round corresponding to each target independent variable; secondly, substituting the initial set value and the gradient value of the current round corresponding to each target independent variable into a gradient descent calculation formula corresponding to a preset optimization algorithm, and calculating the iteration value of the current round corresponding to each target independent variable; finally, generating a current iteration independent variable group according to the current iteration value corresponding to each target independent variable, and storing the current iteration independent variable group into a local storage space;

for the N +1 th round of optimization: firstly, obtaining a historical iteration independent variable group, wherein the historical iteration independent variable group is a current iteration independent variable group corresponding to previous optimization or an updated iteration independent variable group, and the historical iteration independent variable group comprises a historical iteration value corresponding to each target independent variable; secondly, substituting the historical iteration value corresponding to each target independent variable into the target function, and calculating the gradient value of the current round corresponding to each target independent variable according to the target function, namely calculating the partial derivative corresponding to each target independent variable according to the target function after substituting the historical iteration value corresponding to each target independent variable into the target function, and determining the partial derivative corresponding to each target independent variable obtained by calculation as the gradient value of the current round corresponding to each target independent variable; thirdly, substituting the historical iteration value and the gradient value of the current round corresponding to each target independent variable into a gradient descent calculation formula corresponding to a preset optimization algorithm, and calculating the iteration value of the current round corresponding to each target independent variable; finally, generating a current iteration independent variable group according to the current iteration value corresponding to each target independent variable, and storing the current iteration independent variable group into a local storage space; wherein N is a positive integer.

Specifically, in this step, when the iteration independent variable group of the current round obtained by the optimization of the current round is not located in the preset feasible region, and the history iteration independent variable group needs to be updated according to the iteration independent variable group of the current round to obtain the updated iteration independent variable group, the history iteration independent variable group can be updated according to the iteration independent variable group of the current round in the following manner, so as to obtain the updated iteration independent variable group:

firstly, the historical iteration independent variable group is updated for a plurality of times according to the iteration value of the current round corresponding to each target independent variable contained in the iteration independent variable group of the current round, thereby obtaining a plurality of intermediate iteration independent variable groups, determining the intermediate iteration independent variable group obtained by the last round of updating as an updating iteration independent variable group, wherein, the number of the updating rounds is the same as the number of the target independent variables, after each round of updating, whether the intermediate iteration independent variable group obtained by the updating round is positioned in the preset feasible region is judged, if the intermediate iteration independent variable group is positioned in the preset feasible region, then the updating of the current round is reserved, the next round of updating is carried out based on the intermediate iteration independent variable group, if the intermediate iteration independent variable group is not positioned in the preset feasible region, the updating of the current round is abandoned, the gradient value of the current round of the target independent variable corresponding to the updating of the current round is updated to be zero, and the next round of updating is carried out.

For example, a first round of updating is performed, the current round of iteration value corresponding to a first target independent variable included in the current round of iteration independent variable group is used to update the historical iteration value corresponding to a first target independent variable included in the historical iteration independent variable group (the current round of iteration independent variable group includes a plurality of target independent variables whose arrangement sequence is the same as the arrangement sequence of the historical iteration independent variable group including a plurality of target independent variables), so as to obtain a first intermediate iteration independent variable group, whether the first intermediate iteration independent variable group is located in the preset feasible region or not is judged, if the first intermediate iteration independent variable group is located in the preset feasible region, the current round of updating is retained, and a next round of updating is performed based on the first intermediate iteration independent variable group (that is, in a second round of updating, the current round of iteration value corresponding to a second target independent variable included in the current round of iteration independent variable group is used to update the historical iteration value corresponding to a second target independent variable included in the first intermediate iteration independent variable group), if the first intermediate iteration independent variable group is not located in the preset feasible region, abandoning the current round of updating, updating the current round of gradient value corresponding to the first target independent variable to zero, and entering the next round of updating (namely, in the second round of updating, updating the historical iteration value corresponding to the second target independent variable contained in the historical iteration independent variable group by using the current round of iteration value corresponding to the second target independent variable contained in the current round of iteration independent variable group); performing a second round of updating, updating the historical iteration value corresponding to a second target independent variable included in the first intermediate iteration independent variable group (or the historical iteration independent variable group) by using the current round of iteration value corresponding to a second target independent variable included in the current round of iteration independent variable group, thereby obtaining a second intermediate iteration independent variable group, judging whether the second intermediate iteration independent variable group is located in the preset feasible region, if the second intermediate iteration independent variable group is located in the preset feasible region, keeping the current round of updating, and performing the next round of updating based on the second intermediate iteration independent variable group (namely in the third round of updating, updating the historical iteration value corresponding to a third target independent variable included in the second intermediate iteration independent variable group by using the current round of iteration value corresponding to a third target independent variable included in the current round of iteration independent variable group), if the second intermediate iteration independent variable group is not located in the preset feasible region, then the update of the current round is abandoned, the gradient value of the current round corresponding to the second target independent variable is updated to zero, and the next round of update is entered [ namely, in the third round of update, the current round iteration value corresponding to the third target independent variable contained in the current round of iteration independent variable group is used for updating the historical iteration value corresponding to the third target independent variable contained in the first intermediate iteration independent variable group (or the historical iteration independent variable group) ], and so on until the multiple rounds of update are completed.

Further, in this embodiment of the present application, when there is a maintenance parameter corresponding to a preset optimization algorithm, after each round of optimization, when a current iteration independent variable group obtained by the current round of optimization is not located in a preset feasible region, and a historical iteration independent variable group needs to be updated according to the current iteration independent variable group to obtain an updated iteration independent variable group, because the historical iteration independent variable group is updated according to the current iteration independent variable group, so that in the process of obtaining the updated iteration independent variable group, a current-round gradient value corresponding to one or more target independent variables is updated, and thus a current-round parameter value corresponding to the maintenance parameter obtained by previous calculation is not accurate, the current-round parameter value corresponding to the maintenance parameter needs to be updated, and the updating process specifically includes: firstly, calculating a local update parameter value corresponding to the maintenance parameter according to a local gradient value corresponding to each target independent variable, wherein the specific calculation process can refer to the following steps: calculating the description of the corresponding part of the parameter value of the current round corresponding to the maintenance parameter according to the gradient value of the current round corresponding to each target independent variable, which will not be described again herein in the embodiments of the present invention; and secondly, updating the current round parameter values corresponding to the maintenance parameters by using the current round updating parameter values corresponding to the maintenance parameters in the local storage space.

In order to achieve the above object, according to another aspect of the present application, an embodiment of the present application further provides a storage medium, where the storage medium includes a stored program, where when the program runs, the apparatus where the storage medium is located is controlled to execute the above constraint optimization method for the objective function corresponding to the cement production process model.

In order to achieve the above object, according to another aspect of the present application, an embodiment of the present application further provides a constraint optimization apparatus for a cement production process model corresponding to an objective function, where the apparatus includes a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; and when the program instructions run, executing the constraint optimization method of the cement production process model corresponding to the objective function.

Further, as an implementation of the method shown in fig. 1 and fig. 2, another embodiment of the present application further provides a constraint optimization device for a cement production process model corresponding to an objective function. The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method. The device is applied to efficiently carrying out constraint optimization on an objective function corresponding to a cement production process model, and specifically as shown in fig. 3, the device comprises:

the acquiring unit 31 is configured to acquire an objective function corresponding to a cement production process model and an initial independent variable group corresponding to the objective function, where the objective function includes a plurality of objective independent variables, and the initial independent variable group includes an initial set value corresponding to each objective independent variable;

the optimization unit 32 is configured to perform multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm; wherein the content of the first and second substances,

Further, as shown in fig. 4, the optimization unit 32 includes:

a first optimization module 321, configured to, when there is a maintenance parameter corresponding to the preset optimization algorithm,

Further, as shown in fig. 4, the optimization unit 32 includes:

a second optimization module 322, configured to, when there is no maintenance parameter corresponding to the preset optimization algorithm,

Further, as shown in fig. 4, the optimization unit 32 includes:

an updating module 323, configured to perform multiple rounds of updating on the historical iteration independent variable group according to a current round of iteration values corresponding to each target independent variable, so as to obtain multiple intermediate iteration independent variable groups, and determine the intermediate iteration independent variable group obtained in the last round of updating as the updated iteration independent variable group; wherein the content of the first and second substances,

Further, as shown in fig. 4, the apparatus further includes:

a calculating unit 33, configured to, when there is a maintenance parameter corresponding to the preset optimization algorithm, update, by the optimizing unit 32, a historical iteration independent variable group according to the iteration independent variable group of the current round to obtain an updated iteration independent variable group, and then calculate, according to a gradient value of the current round corresponding to each target independent variable, an update parameter value of the current round corresponding to the maintenance parameter;

an updating unit 34, configured to update, in the local storage space, a current round of parameter values corresponding to the maintenance parameters by using the current round of update parameter values corresponding to the maintenance parameters.

The embodiment of the application provides a constraint optimization method and a constraint optimization device for a target function corresponding to a cement production process model, and can perform multiple rounds of iterative optimization on the target function according to an initial independent variable group corresponding to the target function and a preset optimization algorithm after obtaining the target function corresponding to the cement production process model and the initial independent variable group corresponding to the target function, wherein after each round of optimization, whether the iteration independent variable group obtained by the round of optimization is located in a preset feasible region or not is judged, if the iteration independent variable group is located in the preset feasible region, whether a preset stop condition is reached or not is judged, if so, the iterative optimization is stopped, and if not, the next round of optimization is performed based on the iteration independent variable group; and if the iteration independent variable group of the current round is not located in the preset feasible region, updating the historical iteration independent variable group according to the iteration independent variable group of the current round, so as to obtain an updated iteration independent variable group, judging whether a preset stop condition is met, if so, stopping iteration optimization, and if not, performing next round of optimization based on the updated iteration independent variable group. Since the preset optimization algorithm is specifically an unconstrained optimization algorithm based on a gradient, in the embodiment of the application, the unconstrained optimization algorithm is used for realizing constrained optimization of the objective function corresponding to the cement production process model, so that the constrained optimization of the objective function corresponding to the cement production process model can be efficiently performed.

The constraint optimization device of the cement production process model corresponding to the objective function comprises a processor and a memory, wherein the acquisition unit, the optimization unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, and the objective function corresponding to the cement production process model is efficiently subjected to constraint optimization by adjusting kernel parameters.

The embodiment of the application provides a storage medium, which comprises a stored program, wherein when the program runs, equipment where the storage medium is located is controlled to execute the constraint optimization method of the cement production process model corresponding to the objective function.

The storage medium may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

The embodiment of the application also provides a constraint optimization device of the cement production process model corresponding to the objective function, wherein the device comprises a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; and when the program instructions run, executing the constraint optimization method of the cement production process model corresponding to the objective function.

The embodiment of the application provides equipment, the equipment comprises a processor, a memory and a program which is stored on the memory and can run on the processor, and the following steps are realized when the processor executes the program:

Further, when there is a 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, including:

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, including:

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

Further, when there is a maintenance parameter corresponding to the preset optimization algorithm, after the historical iteration independent variable group is updated according to the current iteration independent variable group to obtain an updated iteration independent variable group, the method further includes:

The present application further provides a computer program product adapted to perform program code for initializing the following method steps when executed on a data processing device: 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 comprises a plurality of objective independent variables, and the initial independent variable group comprises initial set values corresponding to each objective independent variable; performing multiple rounds of iterative optimization on the objective function according to the initial independent variable group and a preset optimization algorithm; after each round of optimization, judging whether a current iteration independent variable group obtained by the current round of optimization is located in a preset feasible region, if so, judging whether a preset stopping condition is reached, if so, stopping the iteration optimization, and if not, performing next round of optimization based on the current iteration independent variable group; if the iteration independent variable group of the current round is not located in the preset feasible region, updating a historical iteration independent variable group according to the iteration independent variable group of the current round to obtain an updated iteration independent variable group, judging whether the preset stopping condition is reached, if so, stopping iteration optimization, and if not, performing next round of optimization based on the updated iteration independent variable group, wherein the historical iteration independent variable group is the iteration independent variable group of the current round corresponding to the previous round of optimization or the updated iteration independent variable group.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, 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 disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A constraint optimization method for a cement production process model corresponding to an objective function is characterized by comprising the following steps:

2. The method of claim 1, wherein performing multiple rounds of iterative optimization on the objective function according to the initial set of arguments and a preset optimization algorithm when there are maintenance parameters corresponding to the preset optimization algorithm comprises:

3. The method of claim 1, wherein 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 set and the preset optimization algorithm comprises:

4. The method according to claim 2 or 3, wherein the updating the historical iterative independent variable set according to the current iteration independent variable set to obtain an updated iterative independent variable set comprises:

5. The method of claim 4, wherein when there is a maintenance parameter corresponding to the preset optimization algorithm, after the updating the historical iterative independent variable set according to the current iteration independent variable set to obtain an updated iterative independent variable set, the method further comprises:

6. A constraint optimization device for a cement production process model corresponding to an objective function is characterized by comprising:

7. The apparatus of claim 6, wherein the optimization unit comprises:

8. The apparatus of claim 6, wherein the optimization unit comprises:

9. A storage medium, characterized in that the storage medium comprises a stored program, wherein when the program runs, the storage medium is controlled to implement the method for constrained optimization of an objective function corresponding to a cement production process model according to any one of claims 1 to 5.

10. A constraint optimization device of a cement production process model corresponding to an objective function is characterized by comprising a storage medium; and one or more processors, the storage medium coupled with the processors, the processors configured to execute program instructions stored in the storage medium; the program instructions when executed perform a method of constrained optimization of a corresponding objective function of a cement production process model as claimed in any one of claims 1 to 5.