CN114358426A - Ceramic formula optimization method and system - Google Patents
Ceramic formula optimization method and system Download PDFInfo
- Publication number
- CN114358426A CN114358426A CN202210011011.4A CN202210011011A CN114358426A CN 114358426 A CN114358426 A CN 114358426A CN 202210011011 A CN202210011011 A CN 202210011011A CN 114358426 A CN114358426 A CN 114358426A
- Authority
- CN
- China
- Prior art keywords
- formula
- ceramic
- optimization
- data
- raw material
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of ceramic production, in particular to a ceramic formula optimization method and a ceramic formula optimization system, which comprise the following steps: collecting prior knowledge data of a formula, constructing a prior knowledge base of the ceramic formula, and collecting historical formula data and raw material data of ceramic production to construct a historical formula database of the ceramic; according to the priori knowledge, the raw material data and the historical formula data, integrated learning of knowledge drive and data drive is adopted to construct a ceramic formula performance prediction model; defining the optimization problem of the raw materials of the ceramic formula as a single-target or multi-target optimization problem with constraints and mixed variables, and constructing an optimization model; optimizing the formula by using a data-driven evolution optimization algorithm; constraint processing, robust optimization and multi-solution optimization are sequentially carried out; based on the model and the optimization algorithm, a ceramic raw material formula optimization system is integrated and developed; the invention has the effect of solving the problems of efficiency of optimization design of ceramic formula and trial and error cost.
Description
Technical Field
The invention relates to the technical field of ceramic production, in particular to a method and a system for optimizing a ceramic formula.
Background
At present, the ceramic raw material formula design is very dependent on the prior knowledge of a technical engineer, and the problems of high trial and error cost and low formula design efficiency exist.
The existing ceramic formula optimization and design mainly depend on two methods, one method is that a plurality of formulas are obtained by calculation completely depending on manual experience; the other method is that an excel tool is manually used for formulation design, and then manual tests are carried out, and the working flow is as follows: a technical engineer screens out a plurality of raw materials to design and optimize the formula through judging the raw materials, and determines a plurality of ceramic formula schemes; the designed various formula schemes are manually proportioned for testing, and a better formula scheme is screened in an orthogonal test mode.
The above formula optimization design methods are designed and determined based on subjective experience of people, but considering the limitation of human knowledge storage and the limitation of problem consideration, the existing methods are not only low in efficiency, but also high in trial and error cost, and meanwhile, the obtained formula cannot be judged to be the optimal formula scheme.
Therefore, a data-driven intelligent method for optimizing and calculating a ceramic raw material formula needs to be researched, and an intelligent ceramic body formula optimizing system is constructed and serves as a tool for designing the practicability and universality of a ceramic production formula.
Disclosure of Invention
Aiming at the defects, the invention aims to provide a method and a system for optimizing a ceramic formula, and solves the problems of efficiency of optimization design of the ceramic formula and trial-and-error cost.
In order to achieve the purpose, the invention adopts the following technical scheme:
the ceramic formula optimization method comprises the following steps:
A. collecting prior knowledge data of a formula, constructing a prior knowledge base of the ceramic formula, and collecting historical formula data and raw material data of ceramic production to construct a historical formula database of the ceramic;
B. according to the priori knowledge, the raw material data and the historical formula data, integrated learning of knowledge drive and data drive is adopted to construct a ceramic formula performance prediction model;
C. defining the optimization problem of the raw materials of the ceramic formula as a single-target or multi-target optimization problem with constraints and mixed variables, and constructing an optimization model;
D. optimizing the formula by using a data-driven evolution optimization algorithm;
E. constraint processing, robust optimization and multi-solution optimization are sequentially carried out;
F. based on the model and the optimization algorithm, a ceramic raw material formula optimization system is integrated and developed.
Preferably, the step B of constructing the ceramic formula performance prediction model includes the following steps:
b1. according to a ceramic formula prior rule contained in a ceramic formula prior knowledge base, adopting an ant colony mining system algorithm and a genetic programming method to construct a decision tree and generating a decision tree model based on rule reasoning;
b2. establishing a regression and classification model based on a machine learning method according to a ceramic historical formula database;
b3. and integrating a decision tree model and a machine learning method through an integrated learning mechanism to realize a ceramic formula performance prediction model integrating data and knowledge drive.
Preferably, the step C of constructing the optimization model includes the following steps:
c1. setting the quantity and the types of raw materials of a formula;
c2. determining raw materials according to the price;
c3. and adding constraint conditions into the ceramic formula performance prediction model to form a constraint-carrying optimization mathematical model.
Preferably, the step b1 of generating the decision tree model by using the ant colony mining system algorithm and the genetic programming method includes the following steps:
inputting the number m of raw material types, and setting the number Nc of initialization circulation times to be 0;
setting the type k of the initialized raw material to be 1, sequentially selecting the next raw material according to the ceramic historical formula database, namely the type k of the raw material to be k +1, modifying a taboo table, circulating until k is more than or equal to m, and finishing the circulation;
updating the obtained raw material data when the cycle is finished, judging whether the formula requirements are met, if so, carrying out online inspection to judge whether the formula requirements are met, and if so, outputting a result; if the formula requirements are not met or the online inspection is unqualified, the circulation times Nc are equal to Nc +1, and the circulation is performed again.
Preferably, the robust optimization step uses a robust optimization mechanism based on probability distribution; the multi-solution optimization uses a niche-based multi-solution optimization mechanism.
The ceramic formula optimization system comprises a data acquisition module, a model construction module and a formula optimization module;
the data acquisition module is used for acquiring formula prior knowledge data, raw material data and historical formula data, and constructing a ceramic formula prior knowledge base and a ceramic historical formula database;
the model building module is used for building a ceramic formula performance prediction model;
the formula optimization module is used for constructing an optimization model, optimizing a formula by using a data-driven evolution optimization algorithm, and performing constraint processing, robust optimization and multi-solution optimization;
the data acquisition module, the model building module and the formula optimization module are electrically connected.
Preferably, a first operation submodule is arranged in the model construction module, and the first operation submodule generates a decision tree model by using an ant colony mining system algorithm and a genetic programming method, and includes the following contents:
inputting the number m of raw material types, and setting the number Nc of initialization circulation times to be 0;
setting the type k of the initialized raw material to be 1, sequentially selecting the next raw material according to the ceramic historical formula database, namely the type k of the raw material to be k +1, modifying a taboo table, circulating until k is more than or equal to m, and finishing the circulation;
updating the obtained raw material data when the cycle is finished, judging whether the formula requirements are met, if so, carrying out online inspection to judge whether the formula requirements are met, and if so, outputting a result; if the formula requirements are not met or the online inspection is unqualified, the circulation times Nc are equal to Nc +1, and the circulation is performed again.
Preferably, a second operation submodule is arranged in the formula optimization module and used for performing operations of a data-driven evolution optimization algorithm, robust optimization based on probability distribution and multi-solution optimization based on niches.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the ceramic recipe optimization method as described above when executing the program.
A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the ceramic recipe optimization method as described above.
The technical scheme comprises the following beneficial effects:
on the basis of the ceramic raw material data accumulated at present and the prior knowledge of a technical engineer, a ceramic formula performance prediction model driven by data and the prior knowledge is researched, and a decision tree model based on the prior knowledge and a machine learning model based on historical formula data are fused to realize prediction and evaluation of the ceramic raw material formula performance; defining the optimization problem of the raw materials of the ceramic formula as a single-target or multi-target optimization problem with constraints and mixed variables, and designing an evolution calculation method to realize formula optimization; in addition, aiming at the problems of inaccuracy and instability of a ceramic formula performance prediction model and reasonability and interpretability of a generation solution of a data-driven evolution optimization algorithm, a robust multi-solution formula optimization algorithm is provided, a plurality of candidate formulas with excellent prediction performance can be provided for a technical engineer at the same time, so that the technical engineer can conveniently select a more reasonable formula for trial production, the efficiency of ceramic formula optimization design can be improved, the time of formula test is shortened, the trial-and-error cost of the formula is reduced, and the problem of dependence of a formula design process on the technical engineer is solved.
Drawings
FIG. 1 is a schematic overall flow diagram of an embodiment of the present invention;
FIG. 2 is a flowchart of the step B of constructing a model for predicting the properties of a ceramic formulation in an embodiment of the present invention;
FIG. 3 is a flowchart of the step C of building the optimization model according to the embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention. Furthermore, features defined as "first" and "second" may explicitly or implicitly include one or more of the features for distinguishing between descriptive features, non-sequential, non-trivial and non-trivial.
In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The ceramic formula optimization method and system according to the embodiment of the invention are described below with reference to fig. 1 to 3:
the ceramic formula optimization method comprises the following steps:
A. collecting prior knowledge data of a formula, constructing a prior knowledge base of the ceramic formula, and collecting historical formula data and raw material data of ceramic production to construct a historical formula database of the ceramic;
B. according to the priori knowledge, the raw material data and the historical formula data, integrated learning of knowledge drive and data drive is adopted to construct a ceramic formula performance prediction model;
C. defining the optimization problem of the raw materials of the ceramic formula as a single-target or multi-target optimization problem with constraints and mixed variables, and constructing an optimization model;
D. optimizing the formula by using a data-driven evolution optimization algorithm;
E. constraint processing, robust optimization and multi-solution optimization are sequentially carried out;
F. based on the model and the optimization algorithm, a ceramic raw material formula optimization system is integrated and developed.
Specifically, on the basis of the currently accumulated ceramic raw material data and the prior knowledge of a technical engineer, the embodiment researches a ceramic formula performance prediction model driven by the data and the prior knowledge, and fuses a decision tree model based on the prior knowledge and a machine learning model based on historical formula data to realize prediction and evaluation of the ceramic raw material formula performance; defining the optimization problem of the raw materials of the ceramic formula as a single-target or multi-target optimization problem with constraints and mixed variables, and designing an evolution calculation method to realize formula optimization; in addition, aiming at the problems of inaccuracy and instability of a ceramic formula performance prediction model and reasonability and interpretability of a generation solution of a data-driven evolution optimization algorithm, a robust multi-solution formula optimization algorithm is provided, a plurality of candidate formulas with excellent prediction performance can be provided for a technical engineer at the same time, so that the technical engineer can conveniently select a more reasonable formula for trial production, the efficiency of ceramic formula optimization design can be improved, the time of formula test is shortened, the trial-and-error cost of the formula is reduced, and the problem of dependence of a formula design process on the technical engineer is solved.
In this embodiment, the method for obtaining the ceramic formula prior knowledge base includes: the specific background priori knowledge of the ceramic raw material formula is known through docking with ceramic production technical engineers of enterprises, and a ceramic formula priori knowledge base is constructed through knowledge expression to form a series of ceramic formula priori rules in the form of IF Then. In addition, historical formula data of ceramic production, including various successful and failed formulas, are collected and labeled to form a historical formula database of the ceramic.
And in the step D, optimizing the formula by adopting a related algorithm such as a latest hierarchical particle swarm learning optimization algorithm based on the assistance of the classification model.
Preferably, the step B of constructing the ceramic formula performance prediction model includes the following steps:
b1. according to a ceramic formula prior rule contained in a ceramic formula prior knowledge base, adopting an ant colony mining system algorithm and a genetic programming method to construct a decision tree and generating a decision tree model based on rule reasoning;
b2. establishing a regression and classification model based on a machine learning method according to a ceramic historical formula database;
b3. and integrating a decision tree model and a machine learning method through an integrated learning mechanism to realize a ceramic formula performance prediction model integrating data and knowledge drive.
Specifically, the ceramic formula performance prediction model is driven by a ceramic historical formula database and also needs to accord with various ceramic formula priori knowledge and principles accumulated by ceramic production technical engineers to ensure that the constructed model has interpretability and rationality, so that an integrated learning model of knowledge drive and data drive needs to be adopted, and finally the ceramic formula performance prediction model is tested in a test set and newly acquired data and is in butt joint and optimization with the technical engineers to verify the effectiveness of the ceramic formula performance prediction model.
Specifically, data of a ceramic formula prior knowledge base and a ceramic historical formula database, including chemical components and physical data of a ceramic formula, raw material types, the proportion of each raw material and the like are used as model training and rule bases; and combining the database and the ant colony mining and genetic programming methods to find out each optimal raw material one by one to combine an optimal formula system.
After combining various raw materials, matching the raw materials with chemical and physical data of a formula in a ceramic historical formula database to judge whether the raw materials meet requirements, if not, circulating again to search various optimal raw materials to combine the formula; if the raw materials are in accordance with the requirements, an online verification test is carried out, whether the technical requirements are met is judged through various tests, if the technical requirements are met, the results are output, and if the technical requirements are not met, circulation is carried out again to find the optimal raw materials to combine into a formula.
Preferably, the step C of constructing the optimization model includes the following steps:
c1. setting the quantity and the types of raw materials of a formula;
c2. determining raw materials according to the price;
c3. and adding constraint conditions into the ceramic formula performance prediction model to form a constraint-carrying optimization mathematical model.
Specifically, a constraint optimization mathematical model of the ceramic formula is constructed on the basis of a ceramic formula performance prediction model by combining conditions such as production cost, product category, quality requirements and the like; wherein the constraint conditions comprise production cost, chemical component constraint, dosage constraint, classified dosage constraint and the like; the formula optimization is realized by designing an evolution calculation method by defining the optimization problem of the raw materials of the ceramic formula as a single-target or multi-target optimization problem with constraints and mixed variables.
Preferably, the step b1 of generating the decision tree model by using the ant colony mining system algorithm and the genetic programming method includes the following steps:
inputting the number m of raw material types, and setting the number Nc of initialization circulation times to be 0;
setting the type k of the initialized raw material to be 1, sequentially selecting the next raw material according to the ceramic historical formula database, namely the type k of the raw material to be k +1, modifying a taboo table, circulating until k is more than or equal to m, and finishing the circulation;
updating the obtained raw material data when the cycle is finished, judging whether the formula requirements are met, if so, carrying out online inspection to judge whether the formula requirements are met, and if so, outputting a result; if the formula requirements are not met or the online inspection is unqualified, the circulation times Nc are equal to Nc +1, and the circulation is performed again.
Preferably, the robust optimization step uses a robust optimization mechanism based on probability distribution; the multi-solution optimization uses a niche-based multi-solution optimization mechanism.
Specifically, in practical application, the evolutionary optimization algorithm needs to be further optimized. The complexity of the actual ceramic production process puts new requirements on the design of an optimization algorithm, for example, because the trial-and-error cost is huge, an off-line data-driven optimization mode must be adopted as much as possible in the optimization process, and unnecessary trial-and-error times are reduced; the formula needs to meet a plurality of constraint conditions such as cost, raw material quality and the like; due to the uncertainty of the ceramic formula performance prediction model, a solution generated by an evolution optimization algorithm is required to have higher robustness, and meanwhile, the solution is required to have reasonability and interpretability, and meet the technical cognition of the industry and the like. Aiming at the complex characteristics, mechanisms such as robust optimization based on probability distribution, multi-solution optimization based on niches and the like are required to be adopted, so that a plurality of optimized solutions can be provided for enterprises in one algorithm operation, technical engineers can select solutions with high rationality and interpretability for trial-and-error making, trial-and-error cost is effectively reduced, and production efficiency is improved.
Specifically, a robust optimization mechanism based on probability distribution is used to improve the optimization performance of the algorithm: according to the distribution of the current solution in the search space, candidate solutions are selected according to the probability, information obtained by evolution can be fully utilized, search is carried out around effective information, the capability of an algorithm for exploring a region with less information is also kept, the diversity of the population is ensured, and the situation that the population is trapped in local optimum is avoided; the niche-based multi-solution optimization mechanism can prevent all individuals from converging to a region, so that solutions with larger differences and satisfying constraints are provided, and a plurality of optimized solutions are finally obtained for technical engineers to select.
The embodiment also discloses a ceramic formula optimization system, which comprises a data acquisition module, a model construction module and a formula optimization module;
the data acquisition module is used for acquiring formula prior knowledge data, raw material data and historical formula data, and constructing a ceramic formula prior knowledge base and a ceramic historical formula database;
the model building module is used for building a ceramic formula performance prediction model;
the formula optimization module is used for constructing an optimization model, optimizing a formula by using a data-driven evolution optimization algorithm, and performing constraint processing, robust optimization and multi-solution optimization;
the data acquisition module, the model building module and the formula optimization module are electrically connected.
Preferably, a first operation submodule is arranged in the model construction module, and the first operation submodule generates a decision tree model by using an ant colony mining system algorithm and a genetic programming method, and includes the following contents:
inputting the number m of raw material types, and setting the number Nc of initialization circulation times to be 0;
setting the type k of the initialized raw material to be 1, sequentially selecting the next raw material according to the ceramic historical formula database, namely the type k of the raw material to be k +1, modifying a taboo table, circulating until k is more than or equal to m, and finishing the circulation;
updating the obtained raw material data when the cycle is finished, judging whether the formula requirements are met, if so, carrying out online inspection to judge whether the formula requirements are met, and if so, outputting a result; if the formula requirements are not met or the online inspection is unqualified, the circulation times Nc are equal to Nc +1, and the circulation is performed again.
Preferably, a second operation submodule is arranged in the formula optimization module and used for performing operations of a data-driven evolution optimization algorithm, robust optimization based on probability distribution and multi-solution optimization based on niches.
The present embodiment also discloses an electronic device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the ceramic recipe optimization method as described above.
The present embodiment also discloses a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the ceramic recipe optimization method as described above.
Other configurations and operations of the ceramic formulation optimization method and system according to embodiments of the present invention are known to those of ordinary skill in the art and will not be described in detail herein.
The modules in the ceramic formulation optimization system can be realized in whole or in part by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the electronic device, and can also be stored in a memory of the electronic device in a software form, so that the processor can call and execute operations corresponding to the modules.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, the computer program can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above.
The above description of the embodiments of the present invention is provided for the purpose of illustrating the technical lines and features of the present invention and is provided for the purpose of enabling those skilled in the art to understand the contents of the present invention and to implement the present invention, but the present invention is not limited to the above specific embodiments. It is intended that all such changes and modifications as fall within the scope of the appended claims be embraced therein.
Claims (10)
1. The ceramic formula optimization method is characterized by comprising the following steps:
A. collecting prior knowledge data of a formula, constructing a prior knowledge base of the ceramic formula, and collecting historical formula data and raw material data of ceramic production to construct a historical formula database of the ceramic;
B. according to the priori knowledge, the raw material data and the historical formula data, integrated learning of knowledge drive and data drive is adopted to construct a ceramic formula performance prediction model;
C. defining the optimization problem of the raw materials of the ceramic formula as a single-target or multi-target optimization problem with constraints and mixed variables, and constructing an optimization model;
D. optimizing the formula by using a data-driven evolution optimization algorithm;
E. constraint processing, robust optimization and multi-solution optimization are sequentially carried out;
F. based on the model and the optimization algorithm, a ceramic raw material formula optimization system is integrated and developed.
2. The method of optimizing a ceramic formulation of claim 1, wherein: and B, constructing a ceramic formula performance prediction model, which comprises the following contents:
b1. according to a ceramic formula prior rule contained in a ceramic formula prior knowledge base, adopting an ant colony mining system algorithm and a genetic programming method to construct a decision tree and generating a decision tree model based on rule reasoning;
b2. establishing a regression and classification model based on a machine learning method according to a ceramic historical formula database;
b3. and integrating a decision tree model and a machine learning method through an integrated learning mechanism to realize a ceramic formula performance prediction model integrating data and knowledge drive.
3. The method of optimizing a ceramic formulation of claim 1, wherein: and C, constructing an optimization model in the step C, wherein the construction comprises the following contents:
c1. setting the quantity and the types of raw materials of a formula;
c2. determining raw materials according to the price;
c3. and adding constraint conditions into the ceramic formula performance prediction model to form a constraint-carrying optimization mathematical model.
4. The method of optimizing a ceramic formulation according to claim 2, wherein: the step b1 of generating the decision tree model by adopting the ant colony mining system algorithm and the genetic programming method comprises the following steps:
inputting the number m of raw material types, and setting the number Nc of initialization circulation times to be 0;
setting the type k of the initialized raw material to be 1, sequentially selecting the next raw material according to the ceramic historical formula database, namely the type k of the raw material to be k +1, modifying a taboo table, circulating until k is more than or equal to m, and finishing the circulation;
updating the obtained raw material data when the cycle is finished, judging whether the formula requirements are met, if so, carrying out online inspection to judge whether the formula requirements are met, and if so, outputting a result; if the formula requirements are not met or the online inspection is unqualified, the circulation times Nc are equal to Nc +1, and the circulation is performed again.
5. The method of optimizing a ceramic formulation of claim 1, wherein: the robust optimization step uses a robust optimization mechanism based on probability distribution; the multi-solution optimization uses a niche-based multi-solution optimization mechanism.
6. The ceramic formula optimization system is characterized in that: the system comprises a data acquisition module, a model construction module and a formula optimization module;
the data acquisition module is used for acquiring formula prior knowledge data, raw material data and historical formula data, and constructing a ceramic formula prior knowledge base and a ceramic historical formula database;
the model building module is used for building a ceramic formula performance prediction model;
the formula optimization module is used for constructing an optimization model, optimizing a formula by using a data-driven evolution optimization algorithm, and performing constraint processing, robust optimization and multi-solution optimization;
the data acquisition module, the model building module and the formula optimization module are electrically connected.
7. The ceramic recipe optimization system according to claim 6, wherein: the model construction module is internally provided with a first operation submodule which generates a decision tree model by using an ant colony mining system algorithm and a genetic programming method, and the model construction module comprises the following contents:
inputting the number m of raw material types, and setting the number Nc of initialization circulation times to be 0;
setting the type k of the initialized raw material to be 1, sequentially selecting the next raw material according to the ceramic historical formula database, namely the type k of the raw material to be k +1, modifying a taboo table, circulating until k is more than or equal to m, and finishing the circulation;
updating the obtained raw material data when the cycle is finished, judging whether the formula requirements are met, if so, carrying out online inspection to judge whether the formula requirements are met, and if so, outputting a result; if the formula requirements are not met or the online inspection is unqualified, the circulation times Nc are equal to Nc +1, and the circulation is performed again.
8. The ceramic recipe optimization system according to claim 6, wherein: and a second operation submodule is arranged in the formula optimization module and is used for performing data-driven evolution optimization algorithm, robust optimization based on probability distribution and operation of multi-solution optimization based on niches.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the ceramic recipe optimization method according to any one of claims 1 to 5.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the ceramic recipe optimization method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011011.4A CN114358426A (en) | 2022-01-05 | 2022-01-05 | Ceramic formula optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011011.4A CN114358426A (en) | 2022-01-05 | 2022-01-05 | Ceramic formula optimization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114358426A true CN114358426A (en) | 2022-04-15 |
Family
ID=81107709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210011011.4A Pending CN114358426A (en) | 2022-01-05 | 2022-01-05 | Ceramic formula optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358426A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116661404A (en) * | 2023-07-31 | 2023-08-29 | 江苏海企技术工程股份有限公司 | Metering and batching mixing control method and system based on data fusion |
-
2022
- 2022-01-05 CN CN202210011011.4A patent/CN114358426A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116661404A (en) * | 2023-07-31 | 2023-08-29 | 江苏海企技术工程股份有限公司 | Metering and batching mixing control method and system based on data fusion |
| CN116661404B (en) * | 2023-07-31 | 2023-09-29 | 江苏海企技术工程股份有限公司 | Metering and batching mixing control method and system based on data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6678668B2 (en) | System and method for complex process optimization and control | |
| CN110222387B (en) | Multi-element drilling time sequence prediction method based on mixed leaky integration CRJ network | |
| CN108780313B (en) | Method, system, and computer-readable medium for performing targeted parameter analysis for an assembly line | |
| Lin et al. | Integration of process planning and scheduling for distributed flexible job shops | |
| CN114358426A (en) | Ceramic formula optimization method and system | |
| CN113822388B (en) | Parameter setting method, device, electronic device and storage medium | |
| Chang et al. | Multi-mode plant-wide process operating performance assessment based on a novel two-level multi-block hybrid model | |
| CN111766179A (en) | Limestone slurry density measurement method, system and equipment based on LSSVM | |
| CN107545101A (en) | A kind of design object and the Optimization Design that design variable is section | |
| CN115755954A (en) | Routing inspection path planning method and system, computer equipment and storage medium | |
| CN116204445A (en) | Test case generation method and device, code test method, device and medium | |
| CN114254915A (en) | Method for deciding and optimizing qualified state of full-flow processing quality of shaft parts | |
| CN107292320A (en) | System and its index optimization method and device | |
| Avdeenko et al. | Formulation and research of new fitness function in the genetic algorithm for maximum code coverage | |
| CN116756508A (en) | Fault diagnosis method and device for transformer, computer equipment and storage medium | |
| CN106776088A (en) | Diagnosis method for system fault based on Malek models | |
| Fu et al. | Advanced quality control for probe precision forming to empower virtual vertical integration for semiconductor manufacturing | |
| Liu et al. | A new hypervolume-based differential evolution algorithm for many-objective optimization | |
| Zăvoianu et al. | A soft-computing framework for automated optimization of multiple product quality criteria with application to micro-fluidic chip production | |
| CN114881158A (en) | Defect value filling method and device based on random forest and computer equipment | |
| Yuguang et al. | Clustering and group selection of interim product in shipbuilding | |
| Borràs-Ferrís et al. | Defining multivariate raw material specifications via SMB-PLS | |
| CN111589284A (en) | Stepwise regression data processing method for ammonia injection control system | |
| Neto et al. | Optimization techniques for the selection of members and attributes in ensemble systems | |
| Meiners et al. | Potential of a machine learning based cross-process control in lithium-ion battery production |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |