CN116522806B - Polishing process parameter optimization method, polishing system, electronic device and storage medium - Google Patents
Polishing process parameter optimization method, polishing system, electronic device and storage medium Download PDFInfo
- Publication number
- CN116522806B CN116522806B CN202310805671.4A CN202310805671A CN116522806B CN 116522806 B CN116522806 B CN 116522806B CN 202310805671 A CN202310805671 A CN 202310805671A CN 116522806 B CN116522806 B CN 116522806B
- Authority
- CN
- China
- Prior art keywords
- polishing
- surface roughness
- polishing process
- process parameter
- values
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007517 polishing process Methods 0.000 title claims abstract description 166
- 238000005498 polishing Methods 0.000 title claims abstract description 160
- 238000000034 method Methods 0.000 title claims abstract description 99
- 238000005457 optimization Methods 0.000 title claims abstract description 62
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 230000003746 surface roughness Effects 0.000 claims abstract description 159
- 239000011159 matrix material Substances 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 30
- 238000011156 evaluation Methods 0.000 claims description 28
- 238000005070 sampling Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002068 genetic effect Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 238000012854 evaluation process Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 5
- 238000003908 quality control method Methods 0.000 abstract description 5
- 238000002474 experimental method Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 239000004973 liquid crystal related substance Substances 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010845 search algorithm Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000004439 roughness measurement Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B1/00—Processes of grinding or polishing; Use of auxiliary equipment in connection with such processes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/006—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation taking regard of the speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/16—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation taking regard of the load
- B24B49/165—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation taking regard of the load for grinding tyres
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Abstract
The invention relates to the technical field of data processing, and provides a polishing process parameter optimization method, a polishing system, electronic equipment and a storage medium, wherein the polishing process parameter optimization method comprises the steps of firstly obtaining the value of a polishing process parameter of a target workpiece input by a user, wherein the polishing process parameter comprises the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool; and then inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model. According to the method, the surface roughness of the target workpiece after polishing operation of the polishing tool is determined by utilizing the XGBoost algorithm in combination with polishing process parameters such as pressure applied by the polishing tool, the rotating speed and the feeding speed of the polishing tool, so that accurate prediction of the surface roughness can be realized, a theoretical basis is provided for realizing accurate surface quality control subsequently, and the polishing efficiency of the polishing tool is improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a polishing process parameter optimization method, a polishing system, an electronic device, and a storage medium.
Background
In the production process, the polishing treatment of the surface of the workpiece is a key technology, not only can improve the surface roughness, but also is beneficial to improving the performance and the service life of the workpiece, and is widely applied to numerous precision industries. However, the conventional manual polishing method has many disadvantages such as consuming a lot of time and manpower resources, and difficulty in ensuring the stability of the polishing effect. In recent years, with rapid development of robot technology, robot polishing has been widely used in the field of workpiece polishing. The automatic robot polishing process not only reduces manual operation errors and labor cost and improves the working environment and safety of workers, but also improves the production efficiency and ensures the stability of quality. With the continuous progress of the robot technology and the expansion of application fields, the robot polishing technology becomes a key link of future manufacturing industry and processing industry.
Although robotic polishing techniques have been widely used, ensuring that the surface roughness of a workpiece meets target requirements remains a challenge to be addressed. The surface roughness of a workpiece is closely related to polishing process parameters that in turn affect the efficiency and quality of robot polishing. Accordingly, there is a need to provide a polishing process parameter optimization method, a polishing system, an electronic device, and a storage medium.
Disclosure of Invention
The invention provides a polishing process parameter optimization method, a polishing system, electronic equipment and a storage medium, which are used for solving the defects in the prior art.
The invention provides a polishing process parameter optimization method, which comprises the following steps:
acquiring the value of polishing process parameters of a target workpiece input by a user, wherein the polishing process parameters comprise the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool;
inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model;
based on the surface roughness, adopting a multi-target genetic algorithm to determine a plurality of groups of values of polishing process parameters of the polishing tool meeting the surface roughness;
determining an optimal set of values in the plurality of sets of values based on a technical good-bad solution sorting method;
the surface roughness prediction model is obtained by training based on polishing process parameter data carrying a surface roughness label.
According to the polishing process parameter optimization method provided by the invention, the surface roughness prediction model is obtained based on training of the following steps:
based on the polishing process parameter data, determining an initial prediction model by adopting a super-parameter optimization algorithm;
and training the initial prediction model based on the polishing process parameter data to obtain the surface roughness prediction model.
According to the polishing process parameter optimization method provided by the invention, the initial prediction model is determined by adopting a super-parameter optimization algorithm based on the polishing process parameter data, and the method comprises the following steps:
determining a search space of the super parameters, randomly sampling a group of super parameters in the search space, and constructing an initial model based on the super parameters obtained by sampling;
training the initial model based on the polishing process parameter data, and evaluating the performance of the trained initial model;
and repeating the random sampling process, the model construction process, the model training process and the performance evaluation process until the preset times are reached, selecting a group of super parameters corresponding to the initial model with optimal performance after training as optimal super parameters, and constructing the initial prediction model based on the optimal super parameters.
According to the polishing process parameter optimization method provided by the invention, the optimal one of the multiple groups of values is determined based on the technical good-bad solution sorting method, and the method comprises the following steps:
taking each set of values in the plurality of sets of values as an evaluation object, taking the polishing process parameters as evaluation indexes, and determining to construct an initial decision matrix based on the number of the sets of values and the number of the polishing process parameters;
calculating a weighted decision matrix corresponding to the initial decision matrix based on the occurrence times of the polishing process parameters in the surface roughness prediction model;
and determining an optimal set of values in the plurality of sets of values based on the weighted decision matrix.
According to the polishing process parameter optimization method provided by the invention, the determining of the optimal set of values in the plurality of sets of values based on the weighted decision matrix comprises the following steps:
determining a maximum value and a minimum value in the weighted decision matrix;
and calculating the score of each group of values in the multiple groups of values based on a first distance between each element corresponding to the evaluation object in the weighted decision matrix and the maximum value and a second distance between each element corresponding to the evaluation object in the weighted decision matrix and the minimum value, and taking the group of values with the highest score as the optimal group of values in the multiple groups of values.
According to the polishing process parameter optimization method provided by the invention, the optimal one of the multiple groups of values is determined based on the technical good-bad solution sorting method, and then the method comprises the following steps:
based on the optimal one of the multiple groups of values, polishing the target workpiece by adopting the polishing tool to obtain the actual surface roughness of the target workpiece;
and updating the surface roughness prediction model by taking the optimal value set and the actual surface roughness in the plurality of value sets as polishing process parameter data carrying a surface roughness label.
The present invention also provides a polishing system comprising: the device comprises an industrial robot, a magnetic polishing table, an A-FDC axial force position compensator, a servo motor, a polishing tool and a controller;
the industrial robot, the A-FDC axial force position compensator, the servo motor and the polishing tool are sequentially connected, the controller is respectively connected with the industrial robot, the A-FDC axial force position compensator and the servo motor, and the magnetic polishing table is used for bearing the target workpiece;
the controller is used for executing any polishing process parameter optimization method, determining the value of the polishing process parameter of the polishing tool, and controlling the industrial robot, the A-FDC axial force position compensator and the servo motor to drive the polishing tool to polish the target workpiece.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor implements any one of the polishing process parameter optimization methods described above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements any of the polishing process parameter optimization methods described above.
Compared with the prior art, the invention has the following beneficial effects:
according to the polishing process parameter optimization method, the polishing system, the electronic equipment and the storage medium, firstly, the value of the polishing process parameter of the target workpiece input by a user is obtained, and the polishing process parameter comprises the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool; and then inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model. According to the method, the surface roughness of the target workpiece after polishing operation of the polishing tool is determined by utilizing the XGBoost algorithm in combination with polishing process parameters such as pressure applied by the polishing tool, the rotating speed of the polishing tool and the feeding speed, so that accurate prediction of the surface roughness can be realized, a theoretical basis is provided for realizing accurate surface quality control subsequently, and the polishing efficiency of the polishing tool is improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort.
FIG. 1 is a flow chart of a polishing surface roughness prediction method provided by the invention;
FIG. 2 is a schematic diagram of a training flow of a surface roughness prediction model in the polishing surface roughness prediction method provided by the invention;
FIG. 3 is a schematic flow chart of the polishing process parameter optimization method provided by the invention;
FIG. 4 is a second flow chart of the polishing process parameter optimization method according to the present invention;
FIG. 5 is a third flow chart of the polishing process parameter optimization method according to the present invention;
FIG. 6 is a schematic view of the structure of a polishing system provided by the present invention;
FIG. 7 is a schematic view of a structure of a polishing surface roughness predicting apparatus provided by the present invention;
FIG. 8 is a schematic structural view of a polishing process parameter optimizing apparatus provided by the present invention;
fig. 9 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a schematic flow chart of a polishing surface roughness prediction method provided in an embodiment of the present invention, as shown in fig. 1, the method includes:
s11, acquiring values of polishing process parameters of a target workpiece input by a user, wherein the polishing process parameters comprise pressure applied by a polishing tool, and the rotating speed and the feeding speed of the polishing tool;
s12, inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model;
the surface roughness prediction model is obtained by training based on polishing process parameter data carrying a surface roughness label.
Specifically, in the polishing surface roughness prediction method provided in the embodiment of the present invention, the execution body is a polishing surface roughness prediction device, and the device may be configured in a computer, where the computer may be a local computer or a cloud computer, and the local computer may be a computer, a tablet, or the like, and is not limited herein specifically.
First, step S11 is performed to obtain values of polishing process parameters of the target workpiece input by the user, where the polishing process parameters include pressure applied by the polishing tool, and rotational speed and feed speed of the polishing tool. The target workpiece is a workpiece to be polished by a polishing tool, and may be a steel plate or the like, and is not particularly limited herein.
The polishing process parameters may include a pressure (P) applied by the polishing tool, a rotational speed (R) of the polishing tool, and a feed rate (V). Here, the feed speed is a relative displacement of the target workpiece and the polishing tool in the feed direction per unit time, and the unit may be mm/min.
And then, executing step S12, inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by a polishing tool based on an XGBoost algorithm by the surface roughness prediction model.
Here, the surface roughness prediction model has polishing process parameters as input features and surface roughness as output features. It is understood that the surface roughness is average surface roughness (Ra average).
The surface roughness prediction model is constructed based on an XGBoost algorithm, and the initial prediction model is trained by utilizing polishing process parameter data carrying a surface roughness label.
Polishing process parameter data can be obtained by setting an LN orthogonal table to carry out polishing experiments, designating pressure (P), rotating speed (R) and feeding speed (V) to carry out polishing operation on a sample workpiece, and carrying out roughness measurement on different polishing tracks by using a surface roughness measuring instrument. N groups of polishing process parameter data can be obtained in the step. Each set of polishing process parameter data includes an input characteristic and an output characteristic.
In order to ensure the prediction performance of the model, the super-parameters of the initial prediction model need to be optimized, and the surface roughness prediction model can be obtained based on training of the following steps:
and determining target superparameters of the initial prediction model by utilizing polishing process parameter data and adopting a superparameter optimization algorithm. The hyper-parametric optimization algorithm may include a grid search algorithm, a bayesian optimization algorithm, a random search algorithm, etc., which is more efficient for adjusting multiple hyper-parameters simultaneously.
Taking a random search algorithm as an example, as shown in fig. 2, in the process of determining an initial prediction model, a search space of the super parameters can be determined first, a set of super parameters are randomly sampled in the search space, and an initial model is built based on the super parameters obtained by sampling. And then, training the initial model by using the polishing process parameter data, and evaluating the performance of the trained initial model. Here, the performance of the initial model may be evaluated using a 5-fold cross-validation method, and a negative mean square error (neg_mse) may be used as a performance evaluation index of the initial model.
And repeating the random sampling process, the model construction process, the model training process and the performance evaluation process until the preset times are reached, and selecting a group of super parameters corresponding to the initial model after training with optimal performance as the optimal super parameters. The current Iteration number is Iteration, and the preset number is iteration=n_iter. The preset number of times n_iter may be set as needed, for example, may be set to 50, i.e., n_iter=50. At this time, the super parameter corresponding to the minimum neg_mse is selected as the optimal super parameter.
And constructing and obtaining an initial prediction model by utilizing the optimal super parameters.
And then training the initial prediction model by using polishing process parameter data to obtain the surface roughness prediction model.
The search space and optimization results of the hyper-parameters are shown in table 1, and the rest of the hyper-parameters use default values.
TABLE 1 search space and optimization results for hyper-parameters
Wherein a set of polishing process parameter data is used as a training sample.
The polishing surface roughness prediction method provided by the embodiment of the invention comprises the steps of firstly obtaining the value of polishing process parameters of a target workpiece input by a user, wherein the polishing process parameters comprise the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool; and then inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model. According to the method, the surface roughness of the target after polishing operation is determined by utilizing the XGBoost algorithm in combination with polishing process parameters such as pressure applied by the polishing tool, the rotating speed and the feeding speed of the polishing tool, so that the accurate prediction of the surface roughness can be realized, a theoretical basis is provided for realizing accurate surface quality control subsequently, and the polishing efficiency of the polishing tool is improved.
And the optimal value of the polishing process parameter can be reversely solved by utilizing the surface roughness of the target workpiece obtained by the surface roughness prediction model. However, due to the complex relationship between surface roughness and polishing process parameters, there may be multiple sets of polishing process parameter combinations that meet one surface roughness at a time. Thus, this is a single objective optimization problem with multiple globally optimal solutions. Meanwhile, in order to ensure the material removal rate during polishing and improve the polishing efficiency, a plurality of global optimal solutions are required to be ordered according to different attributes of polishing process parameters.
In order to effectively solve the above two problems, as shown in fig. 3, an embodiment of the present invention further provides a polishing process parameter optimization method, which includes:
s21, acquiring the surface roughness of the target workpiece, which is determined based on the polishing surface roughness prediction method provided by the embodiment, after polishing operation of the polishing tool;
s22, based on the surface roughness, adopting a multi-target genetic algorithm to determine a plurality of groups of values of polishing process parameters of the polishing tool meeting the surface roughness;
s23, determining the optimal value of the multiple groups of values based on a technical good and bad solution sorting method.
Specifically, the polishing process parameter optimization method provided in the embodiment of the present invention has an execution body that is a polishing process parameter optimization device, and the device may be configured in a computer, where the computer may be a local computer or a cloud computer, and the local computer may be a computer, a tablet, or the like, and is not limited herein specifically.
First, step S21 is performed to obtain the surface roughness of the target workpiece after the polishing work by the polishing tool, which is determined based on the polishing surface roughness prediction method provided in the above embodiment, after receiving the value of the polishing process parameter of the target workpiece input by the user.
Then, step S22 is performed to determine a plurality of sets of values of polishing process parameters of the polishing tool satisfying the surface roughness by using the surface roughness and a multi-objective genetic algorithm. The multi-objective genetic algorithm may be NSGA II algorithm, and multiple sets of globally optimal solutions may be found in a single objective optimization problem.
Finally, step S23 is executed, and the optimal set of values among the plurality of sets of values is determined by using the technique superior-inferior solution sorting method. The technique of the best solution ordering method can be a TOPSIS algorithm.
That is, the polishing process parameter optimization method can adopt NSGA II-TOPSIS dual optimization algorithm to perform polishing process parameter optimization so as to determine a group of values with optimal polishing process parameters.
The polishing process parameter optimization method provided by the embodiment of the invention firstly obtains the surface roughness of the target workpiece, which is determined based on the polishing surface roughness prediction method provided by the embodiment, after polishing operation by a polishing tool; then, based on the surface roughness, adopting a multi-target genetic algorithm to determine a plurality of groups of values of polishing process parameters of the polishing tool meeting the surface roughness; and finally, determining the optimal value of the multiple groups of values based on a technical good and bad solution sorting method. According to the method, the surface roughness determined by the surface roughness prediction model is combined with a multi-target genetic algorithm and a technical quality solution sequencing method to determine a group of values of optimal polishing process parameters, so that the accurate determination of the values of the polishing process parameters can be realized, further, the accurate surface quality control is realized, and the polishing efficiency of a polishing tool can be improved.
As shown in fig. 4, in performing step S22, a problem may be defined first, an optimization target may be determined, and an objective function related to the surface roughness may be established, as shown in formula (1) and formula (2):
； （1）
； （2）
wherein, the liquid crystal display device comprises a liquid crystal display device,a is surface roughness->In particular, when a=0, the optimization objective is surface roughness +.>Is a minimum of (2). />The surface roughness obtained by the surface roughness prediction model is shown.
Then, the number pop_size of the polishing process parameter can be set, for example, to 100, which indicates that the objective function has 100 optimal solutions.
Thereafter, a termination condition may be defined according to the number of optimal solutions of the objective function, e.g., gen=100. Where gen is the number of iterations.
Thereafter, operations such as population initialization, selection, crossover mutation, offspring evaluation, non-dominance ranking, crowding distance, and the like are performed.
Finally, a set of 100 optimal solutions is extracted after the termination condition is satisfied. Here, the 100 optimal solutions are multiple sets of values of polishing process parameters.
When executing step S21, each of the multiple sets of values may be used as an evaluation object, and the polishing process parameter is used as an evaluation index, and the initial decision matrix is established by using the number of the multiple sets of values and the number of the polishing process parameter;
then calculating a weighted decision matrix corresponding to the initial decision matrix by using the occurrence times of the polishing process parameters in the surface roughness prediction model;
and finally, determining the optimal value of the multiple groups of values by using a weighted decision matrix.
Specifically, in the technical merit solution sorting method, the number m of evaluation objects, that is, the number of groups of multiple groups of values, has m=100, the number n of evaluation indexes, that is, the number of polishing process parameters, has n=3, and is the pressure P, the rotation speed R, and the feed speed V, respectively.
The initial decision matrix may be expressed asAnd has:
； （3）
wherein, the liquid crystal display device comprises a liquid crystal display device,i =1,2,...,m；j=1,2,…,n；representing the contribution of the ith evaluation object to the jth evaluation index.
The number of occurrences of the polishing process parameter in the surface roughness prediction model may represent an importance score of the polishing process parameter, which may be calculated by a plot_reporting function in an Xgboost library, and in the embodiment of the present invention, the number of occurrences of the pressure P may be 17, the number of occurrences of the rotation speed R may be 18, and the number of occurrences of the feed speed V may be 26.
And calculating a weighted decision matrix corresponding to the initial decision matrix by using the occurrence times of the polishing process parameters in the surface roughness prediction model. Here, the weight of each evaluation index can be calculated by using the number of occurrences of the polishing process parameterAnd multiplying the weighted decision matrix with the corresponding element in the initial decision matrix Z to obtain a weighted decision matrix +.>And has:
； （4）
and finally, determining the optimal value of the multiple groups of values by using the weighted decision matrix. Here, the maximum value in the weighted decision matrix can be determined firstAnd minimum->The method comprises the following steps:
； （5）
； （6）
and then, calculating the score of each group of values in the multiple groups of values by using the first distance between each element corresponding to the evaluation object in the weighted decision matrix and the maximum value and the second distance between each element corresponding to the evaluation object in the weighted decision matrix and the minimum value, and taking the group of values with the highest score as the optimal group of values in the multiple groups of values. Wherein the first distance and the second distance may both be euclidean distances.
The first distance may be calculated by the following formula:
； （7）
the second distance may be calculated by the following formula:
； （8）
the score of each evaluation object, i.e., the score of each set of values, can be calculated according to formula (9) and converted into a percentage score using formula (10).
； （9）
； （10）
Wherein, the liquid crystal display device comprises a liquid crystal display device,score for the ith evaluation object, +.>The percentage fraction of the object is evaluated for the i-th.
And finally, sorting all the evaluation objects according to the scores from high to low to obtain one evaluation object with the highest score, namely an optimal group of values, and recommending the evaluation object to a user for polishing a target workpiece.
Based on the above embodiment, the determining, based on the technology best solution sorting method, an optimal set of values among the plurality of sets of values includes:
based on the optimal one of the multiple groups of values, polishing the target workpiece by adopting the polishing tool to obtain the actual surface roughness of the target workpiece;
and updating the surface roughness prediction model by taking the optimal value set and the actual surface roughness in the plurality of value sets as polishing process parameter data carrying a surface roughness label.
Specifically, after a set of values of optimal polishing process parameters is determined, the set of values may be utilized to perform polishing operation on the target workpiece by using a polishing tool, so as to obtain an actual surface roughness of the target workpiece.
And then, the set of values and the actual surface roughness are used as a set of polishing process parameter data for updating the surface roughness prediction model.
The overall flow of the polishing process parameter optimization method is shown in fig. 5, and comprises the following steps:
performing polishing experiments on the sample workpiece by designating pressure (P), rotating speed (R) and feeding speed (V);
after the experiment is completed, N groups of polishing process parameter data are collected and stored in a database;
training an initial prediction model by utilizing N groups of polishing process parameter data to obtain a surface roughness prediction model;
optimizing polishing process parameters by using NSGA II-TOPSIS double optimization algorithm, and determining a group of values with optimal polishing process parameters;
performing polishing operation by utilizing a group of values with optimal polishing process parameters to obtain the actual surface roughness of the target workpiece;
taking a group of values with optimal polishing process parameters and the actual surface roughness of the target workpiece as a group of polishing process parameter data, and updating a database;
and updating the surface roughness prediction model by using the new database, and predicting the surface roughness of the subsequent target workpiece by using the new surface roughness prediction model.
In theory, N groups of polishing process parameter data obtained through NSGA II algorithm optimization can meet the precision requirement. Therefore, experimental verification needs to be performed on polishing process parameter data obtained through NSGA II algorithm optimization and polishing process parameter data obtained through NSGA II-TOPSIS double optimization algorithm double optimization respectively.
And randomly selecting 3 groups of polishing process parameter data from 100 groups of polishing process parameter data obtained by NSGA II algorithm optimization as the polishing process parameters of a verification experiment 1. The surface roughness predicted by the surface roughness prediction model in experiment I and the surface roughness pairs obtained by the experiment are verified as shown in table 2.
Table 2 verifies the predicted surface roughness and the experimental surface roughness comparison of experiment 1
As can be seen from Table 2, when the optimization objective isRa=0.35 μm orRa=0.45 μm orRaAt minimum, the maximum absolute error of the predicted surface roughness and the experimental surface roughness corresponding to the three groups of polishing process parameter data is 0.02 mu m, and the maximum relative error is<8, the error is within the allowable range. The polishing process parameter combination obtained through NSGA II algorithm optimization can basically meet the processing requirement in precision.
And selecting polishing process parameter data with highest score obtained by NSGA II-TOPSIS double optimization algorithm to carry out verification experiment II. The surface roughness predicted by the surface roughness prediction model in experiment II and the surface roughness pairs obtained by the experiment are verified and shown in table 3.
Table 3 verifies the predicted roughness and experimental roughness comparisons of experiment 2
It can be seen from Table 3 that when the optimization objective isRa=0.45 μm orRa=0.35 μm orRaAt minimum, the maximum absolute error of the predicted surface roughness and the experimental surface roughness corresponding to the three groups of polishing process parameter data is 0.035 mu m, and the maximum relative error is<9%. The error is within the allowable range. In particular, when the optimization objective is minimumRaWhen the feeding speed is increased from 0.25mm/s to 0.37mm/s, the efficiency is increased by 48%. Thus passing through doubleThe re-optimized parameters can meet the precision requirement, improve the processing efficiency to a certain extent, help workers to quickly make decisions, and have guiding significance for actual production.
As shown in fig. 6, on the basis of the above embodiment, there is further provided a polishing system according to an embodiment of the present invention, including: an industrial robot 51, a magnetic polishing table 52, an a-FDC axial force level compensator 53, a servo motor 54, a polishing tool 55, and a controller 56;
the industrial robot 51, the a-FDC axial force position compensator 53, the servo motor 54, and the polishing tool 55 are sequentially connected, and the controller 56 is respectively connected to the industrial robot 51, the a-FDC axial force position compensator 53, and the servo motor 54, and the magnetic polishing table 52 is used for carrying a target workpiece 57.
The controller 56 is configured to execute the polishing process parameter optimization method provided in the above embodiments, determine the value of the polishing process parameter of the polishing tool 55, and control the industrial robot 51, the a-FDC axial force position compensator 53 and the servo motor 54 to drive the polishing tool 55 to perform polishing operation on the target workpiece 57.
According to the polishing system provided by the embodiment of the invention, the value of the polishing process parameter of the polishing tool 55 used for polishing the target workpiece can be accurately determined by executing the polishing process parameter optimization method provided by the embodiments through the controller, and further, the accurate surface quality control can be realized by controlling the industrial robot 51, the A-FDC axial force position compensator 53 and the servo motor 54, so that the polishing efficiency of the polishing tool is improved.
As shown in fig. 7, on the basis of the above embodiment, there is provided a polishing surface roughness predicting apparatus in an embodiment of the present invention, including:
a first obtaining module 61, configured to obtain a value of a polishing process parameter of a target workpiece input by a user, where the polishing process parameter includes a pressure applied by a polishing tool, a rotational speed of the polishing tool, and a feeding speed;
the roughness predicting module 62 is configured to input a value of a polishing process parameter of the target workpiece to a surface roughness predicting model, and determine, by the surface roughness predicting model, a surface roughness of the target workpiece after polishing by the polishing tool based on an XGBoost algorithm;
the surface roughness prediction model is obtained by training based on polishing process parameter data carrying a surface roughness label.
On the basis of the foregoing embodiment, the polishing surface roughness predicting device provided in the embodiment of the present invention further includes a model training module, configured to:
based on the polishing process parameter data, determining an initial prediction model by adopting a super-parameter optimization algorithm;
and training the initial prediction model based on the polishing process parameter data to obtain the surface roughness prediction model.
On the basis of the foregoing embodiments, the polishing surface roughness predicting device provided in the embodiment of the present invention, the model training module is specifically configured to:
determining a search space of the super parameters, randomly sampling a group of super parameters in the search space, and constructing an initial model based on the super parameters obtained by sampling;
training the initial model based on the polishing process parameter data, and evaluating the performance of the trained initial model;
and repeating the random sampling process, the model construction process, the model training process and the performance evaluation process until the preset times are reached, selecting a group of super parameters corresponding to the initial model with optimal performance after training as optimal super parameters, and constructing the initial prediction model based on the optimal super parameters.
Specifically, the functions of each module in the polishing surface roughness predicting device provided in the embodiment of the present invention are in one-to-one correspondence with the operation flows of each step in the above method embodiments, and the achieved effects are consistent.
As shown in fig. 8, on the basis of the above embodiment, an apparatus for optimizing polishing process parameters is provided in an embodiment of the present invention, including:
a second obtaining module 71, configured to obtain a surface roughness of the target workpiece after polishing by the polishing tool, where the surface roughness is determined based on the polishing surface roughness prediction method described above;
an initial value determination module 72, configured to determine, based on the surface roughness, a plurality of sets of values of polishing process parameters of the polishing tool that satisfy the surface roughness using a multi-objective genetic algorithm;
the optimal value determining module 73 is configured to determine an optimal set of values from the multiple sets of values based on a technique better and worse solution sorting method.
On the basis of the foregoing embodiments, the polishing process parameter optimization device provided in the embodiments of the present invention, the optimal value determining module is specifically configured to:
taking each set of values in the plurality of sets of values as an evaluation object, taking the polishing process parameters as evaluation indexes, and determining to construct an initial decision matrix based on the number of the sets of values and the number of the polishing process parameters;
calculating a weighted decision matrix corresponding to the initial decision matrix based on the occurrence times of the polishing process parameters in the surface roughness prediction model;
and determining an optimal set of values in the plurality of sets of values based on the weighted decision matrix.
On the basis of the foregoing embodiment, the polishing process parameter optimization device provided in the embodiment of the present invention determines an optimal set of values among the multiple sets of values based on the weighted decision matrix, where the optimal value determination module is specifically configured to:
determining a maximum value and a minimum value in the weighted decision matrix;
and calculating the score of each group of values in the multiple groups of values based on a first distance between each element corresponding to the evaluation object in the weighted decision matrix and the maximum value and a second distance between each element corresponding to the evaluation object in the weighted decision matrix and the minimum value, and taking the group of values with the highest score as the optimal group of values in the multiple groups of values.
On the basis of the above embodiment, the polishing process parameter optimizing device provided in the embodiment of the present invention further includes a model updating module, configured to:
based on the optimal one of the multiple groups of values, polishing the target workpiece by adopting the polishing tool to obtain the actual surface roughness of the target workpiece;
and updating the surface roughness prediction model by taking the optimal value set and the actual surface roughness in the plurality of value sets as polishing process parameter data carrying a surface roughness label.
Specifically, the functions of each module in the polishing process parameter optimization device provided in the embodiment of the present invention are in one-to-one correspondence with the operation flows of each step in the above method embodiment, and the achieved effects are consistent.
Fig. 9 illustrates a physical schematic diagram of an electronic device, as shown in fig. 9, which may include: processor 810, communication interface (Communications Interface) 820, memory 830, and communication bus 840, wherein Processor 810, communication interface 820, memory 830 accomplish communication with each other through communication bus 840. The processor 810 may invoke logic instructions in the memory 830 to perform the polishing surface roughness prediction method provided in the above embodiments, the method comprising: acquiring the value of polishing process parameters of a target workpiece input by a user, wherein the polishing process parameters comprise the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool; inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model; the surface roughness prediction model is obtained by training based on polishing process parameter data carrying a surface roughness label.
Further, the logic instructions in the memory 830 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, including a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of executing the polishing surface roughness prediction method provided in the above embodiments, the method comprising: acquiring the value of polishing process parameters of a target workpiece input by a user, wherein the polishing process parameters comprise the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool; inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model; the surface roughness prediction model is obtained by training based on polishing process parameter data carrying a surface roughness label.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the polishing surface roughness prediction method provided in the above embodiments, the method comprising: acquiring the value of polishing process parameters of a target workpiece input by a user, wherein the polishing process parameters comprise the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool; inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model; the surface roughness prediction model is obtained by training based on polishing process parameter data carrying a surface roughness label.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A method for optimizing polishing process parameters, comprising:
acquiring the value of polishing process parameters of a target workpiece input by a user, wherein the polishing process parameters comprise the pressure applied by a polishing tool, the rotating speed and the feeding speed of the polishing tool;
inputting the value of the polishing process parameter of the target workpiece into a surface roughness prediction model, and determining the surface roughness of the target workpiece after polishing operation by the polishing tool based on an XGBoost algorithm by the surface roughness prediction model;
based on the surface roughness, adopting a multi-target genetic algorithm to determine a plurality of groups of values of polishing process parameters of the polishing tool meeting the surface roughness;
determining an optimal set of values in the plurality of sets of values based on a technical good-bad solution sorting method; the technical good and bad solution ordering method is a TOPSIS algorithm;
the surface roughness prediction model is obtained by training based on polishing process parameter data carrying a surface roughness label.
2. The polishing process parameter optimization method as recited in claim 1, wherein the surface roughness prediction model is trained based on the steps of:
based on the polishing process parameter data, determining the optimal super parameter of the initial prediction model by adopting a super parameter optimization algorithm;
and training the initial prediction model based on the polishing process parameter data to obtain the surface roughness prediction model.
3. The method of claim 2, wherein determining optimal superparameters of an initial predictive model using a superparameter optimization algorithm based on the polishing process parameter data comprises:
determining a search space of the super parameters, randomly sampling a group of super parameters in the search space, and constructing an initial model based on the super parameters obtained by sampling;
training the initial model based on the polishing process parameter data, and evaluating the performance of the trained initial model;
and repeating the random sampling process, the model construction process, the model training process and the performance evaluation process until the preset times are reached, and selecting a group of super parameters corresponding to the initial model with optimal performance after training as the optimal super parameters.
4. The method according to claim 1, wherein determining an optimal one of the plurality of sets of values based on the technique better-worse solution ordering method comprises:
taking each set of values in the plurality of sets of values as an evaluation object, taking the polishing process parameters as evaluation indexes, and determining to construct an initial decision matrix based on the number of the sets of values and the number of the polishing process parameters;
calculating a weighted decision matrix corresponding to the initial decision matrix based on the occurrence times of the polishing process parameters in the surface roughness prediction model;
and determining an optimal set of values in the plurality of sets of values based on the weighted decision matrix.
5. The method of claim 4, wherein determining an optimal one of the plurality of sets of values based on the weighted decision matrix comprises:
determining a maximum value and a minimum value in the weighted decision matrix;
and calculating the score of each group of values in the multiple groups of values based on a first distance between each element corresponding to the evaluation object in the weighted decision matrix and the maximum value and a second distance between each element corresponding to the evaluation object in the weighted decision matrix and the minimum value, and taking the group of values with the highest score as the optimal group of values in the multiple groups of values.
6. The method according to any one of claims 1 to 5, wherein determining an optimal one of the plurality of sets of values based on the technique better-worse solution ordering method, comprises:
based on the optimal one of the multiple groups of values, polishing the target workpiece by adopting the polishing tool to obtain the actual surface roughness of the target workpiece;
and updating the surface roughness prediction model by taking the optimal value set and the actual surface roughness in the plurality of value sets as polishing process parameter data carrying a surface roughness label.
7. A polishing system, comprising: the device comprises an industrial robot, a magnetic polishing table, an A-FDC axial force position compensator, a servo motor, a polishing tool and a controller;
the industrial robot, the A-FDC axial force position compensator, the servo motor and the polishing tool are sequentially connected, the controller is respectively connected with the industrial robot, the A-FDC axial force position compensator and the servo motor, and the magnetic polishing table is used for bearing the target workpiece;
the controller is used for executing the polishing process parameter optimization method according to any one of claims 1-6, determining the value of the polishing process parameter of the polishing tool, and controlling the industrial robot, the A-FDC axial force position compensator and the servo motor to drive the polishing tool to polish the target workpiece.
8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the polishing process parameter optimization method of any one of claims 1-6 when the program is executed by the processor.
9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the polishing process parameter optimization method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310805671.4A CN116522806B (en) | 2023-07-03 | 2023-07-03 | Polishing process parameter optimization method, polishing system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310805671.4A CN116522806B (en) | 2023-07-03 | 2023-07-03 | Polishing process parameter optimization method, polishing system, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116522806A CN116522806A (en) | 2023-08-01 |
| CN116522806B true CN116522806B (en) | 2023-09-19 |
Family
ID=87401542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310805671.4A Active CN116522806B (en) | 2023-07-03 | 2023-07-03 | Polishing process parameter optimization method, polishing system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116522806B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116690402B (en) * | 2023-08-09 | 2023-11-14 | 浙江晶盛机电股份有限公司 | Method and device for adjusting technological parameters of polishing machine, computer equipment and storage medium |
| CN116842415B (en) * | 2023-09-01 | 2023-12-26 | 广东台正精密机械有限公司 | Remote monitoring method, system and medium for mirror surface electric discharge machine |
| CN117226608B (en) * | 2023-09-19 | 2024-04-02 | 中山市光大光学仪器有限公司 | Polishing control method and system for beam-splitting prism coating film |
| CN117161892B (en) * | 2023-10-25 | 2024-01-26 | 苏州博宏源机械制造有限公司 | Polishing component intelligent control system based on polishing material attribute detection |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104155914A (en) * | 2014-09-01 | 2014-11-19 | 湘潭大学 | CMP process intelligent decision making system for polishing carbide blade |
| CN113910085A (en) * | 2021-09-26 | 2022-01-11 | 江苏集萃华科智能装备科技有限公司 | Control method, control device and control system of metal mirror polishing production line |
| CN115600492A (en) * | 2022-09-27 | 2023-01-13 | 华中科技大学（Cn） | Laser cutting process design method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4700672B2 (en) * | 2006-11-08 | 2011-06-15 | エーエスエムエル マスクツールズ ビー．ブイ． | Method, program, and apparatus for predicting line width roughness and resist pattern defects and their use in lithography simulation processes |
-
2023
- 2023-07-03 CN CN202310805671.4A patent/CN116522806B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104155914A (en) * | 2014-09-01 | 2014-11-19 | 湘潭大学 | CMP process intelligent decision making system for polishing carbide blade |
| CN113910085A (en) * | 2021-09-26 | 2022-01-11 | 江苏集萃华科智能装备科技有限公司 | Control method, control device and control system of metal mirror polishing production line |
| CN115600492A (en) * | 2022-09-27 | 2023-01-13 | 华中科技大学（Cn） | Laser cutting process design method and system |
Non-Patent Citations (1)
| Title |
|---|
| 李婕 ; 史耀耀 ; 何晓东.《航空发动机叶片砂带抛光工艺参数优化》.《航空制造技术》.2016,第1-7页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116522806A (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116522806B (en) | Polishing process parameter optimization method, polishing system, electronic device and storage medium | |
| CN109828532B (en) | GA-GBRT-based surface roughness prediction method and technological parameter optimization method | |
| CN108520111B (en) | Soft measurement method based on optimal selection and optimal regression of orthogonal components | |
| CN110070235B (en) | Flexible scheduling method for multiple mobile robots | |
| US20160335548A1 (en) | Methods and apparatus for predicting fault occurrence in mechanical systems and electrical systems | |
| CN110221580B (en) | Feed speed optimization method based on main shaft data simulation | |
| CN111752151A (en) | Adaptive tracking and compensating method and system for grinding and polishing industrial blade | |
| CN108022004A (en) | A kind of adaptive weighting training method of multi-model weighted array Forecasting Power System Load | |
| CN114493337A (en) | Flexible job shop scheduling method based on improved particle swarm genetic hybrid algorithm | |
| CN114002946A (en) | Self-adaptive PID parameter setting method, system, electronic equipment and storage medium | |
| CN112381343A (en) | Flexible job shop scheduling method based on genetic-backbone particle swarm hybrid algorithm | |
| CN112907150A (en) | Production scheduling method based on genetic algorithm | |
| CN110704959B (en) | MOEAD (Metal oxide optical insulator deposition) optimization fixture layout method and device based on migration behavior | |
| Wang et al. | An intelligent process parameters determination method based on multi-algorithm fusion: A case study in five-axis milling | |
| CN111597645B (en) | Robot deburring optimal process parameter selection method and system | |
| CN117148796A (en) | Optimization method for solving scheduling problem of multi-target flexible job shop | |
| CN111967184A (en) | Sequence model-based multi-target antenna design method | |
| CN111369039A (en) | Alloy heat treatment process optimization method based on multi-objective optimization assisted active learning | |
| CN111222627A (en) | Air knife distance data driving prediction method for plating control | |
| CN116305885A (en) | Method, device and storage medium for predicting or controlling iron loss of silicon steel | |
| CN115640898A (en) | Large-scale flexible job shop scheduling method based on DDQN algorithm | |
| CN113837474A (en) | Regional soil heavy metal pollution index prediction method and device | |
| EP4272215A1 (en) | Protein structure prediction | |
| CN113868765A (en) | Ship main scale parameter optimization method based on approximate model | |
| Wang et al. | A FJSSP Method Based on Dynamic Multi-Objective Squirrel Search Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |