CN114330142A - Self-adaptive matching method for metal mirror polishing process parameters - Google Patents
Self-adaptive matching method for metal mirror polishing process parameters Download PDFInfo
- Publication number
- CN114330142A CN114330142A CN202210011543.8A CN202210011543A CN114330142A CN 114330142 A CN114330142 A CN 114330142A CN 202210011543 A CN202210011543 A CN 202210011543A CN 114330142 A CN114330142 A CN 114330142A
- Authority
- CN
- China
- Prior art keywords
- polishing
- polishing process
- adaptive
- process parameters
- prediction model
- 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
- 238000007517 polishing process Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 47
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 26
- 239000002184 metal Substances 0.000 title claims abstract description 26
- 238000005498 polishing Methods 0.000 claims abstract description 76
- 230000003044 adaptive effect Effects 0.000 claims abstract description 32
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 230000003746 surface roughness Effects 0.000 claims abstract description 14
- 238000004088 simulation Methods 0.000 claims abstract description 9
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 239000002245 particle Substances 0.000 claims description 50
- 238000013528 artificial neural network Methods 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 8
- 238000013459 approach Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 15
- 239000000463 material Substances 0.000 description 9
- 239000006061 abrasive grain Substances 0.000 description 4
- 230000007547 defect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010230 functional analysis Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Landscapes
- Grinding And Polishing Of Tertiary Curved Surfaces And Surfaces With Complex Shapes (AREA)
Abstract
The invention relates to the technical field of metal processing, and particularly discloses a metal mirror polishing process parameter adaptive matching method, which comprises the following steps: obtaining polishing process parameters and test data of corresponding polishing results; constructing a prediction model according to a self-adaptive optimization algorithm, wherein the prediction model can carry out self-learning according to the test data to obtain the mapping relation between the polishing process parameters and the polishing result; inputting the target polishing result into the prediction model to obtain a result of simulation prediction of the prediction model; and taking the result of the simulation prediction as an instructive polishing process parameter for realizing the target polishing result. The metal mirror polishing process parameter adaptive matching method provided by the invention can improve the polishing efficiency and obtain ideal surface roughness.
Description
Technical Field
The invention relates to the technical field of metal processing, in particular to a metal mirror polishing process parameter self-adaptive matching method.
Background
Metal mirror polishing is a complex polishing process, requires a very low surface roughness value Ra with a high polishing efficiency MMR, and has very high requirements on polishing process parameters. The material properties and polishing requirements of the existing mirror polishing workpiece are different, the material removal mechanism is complex, the process parameters are various and are influenced interactively, when the mirror polishing process is tested, the process parameters need to be adjusted manually, the polishing result is observed, the process parameters are adjusted repeatedly according to experience, and the required polishing effect and polishing efficiency are achieved. The test process needs more time and energy, parameters are adjusted by human subjective experience, and accumulated knowledge and experience are difficult to teach among different operators. In addition, the surface roughness is usually measured off-line or after machining is completed, when the surface quality treatment of the part is already finished, which inevitably leads to losses when defects occur.
In the prior art, a polishing method mainly adopted for mirror polishing is a wet physical polishing method, a grinding medium is added between a polishing disk and a workpiece to enable the polishing disk to rotate, a polishing contact force is applied to the polishing disk, and the material removal of the surface of the workpiece is realized by depending on the micro-cutting action of an abrasive in the grinding medium on the surface of the workpiece, so that the mirror polishing is realized. According to the earlier theoretical research, the relationship between the surface roughness value and the material removal rate and the process parameters is complex and interactive, and although the traditional BP neural network algorithm is good at processing the relationship, a large amount of test data is needed to improve the model precision, the convergence rate is low, the generalization capability is poor, and the defect of easily falling into the local optimal solution is overcome.
Therefore, how to improve the polishing efficiency and reduce the surface roughness becomes a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The invention provides a metal mirror polishing process parameter self-adaptive matching method, which solves the problem of low polishing efficiency in the related technology.
As a first aspect of the present invention, there is provided a method for adaptively matching parameters of a metal mirror polishing process, comprising:
obtaining polishing process parameters and test data of corresponding polishing results;
constructing a prediction model according to a self-adaptive optimization algorithm, wherein the prediction model can carry out self-learning according to the test data to obtain the mapping relation between the polishing process parameters and the polishing result;
inputting the target polishing result into the prediction model to obtain a result of simulation prediction of the prediction model;
and taking the result of the simulation prediction as an instructive polishing process parameter for realizing the target polishing result.
Further, the building of the prediction model according to the adaptive optimization algorithm includes:
optimizing the BP neural network according to a self-adaptive particle population algorithm to obtain a self-adaptive optimization algorithm;
constructing an SPSO-BP prediction model according to the self-adaptive optimization algorithm;
the SPSO-BP prediction model can carry out self-learning according to the test data to obtain the mapping relation between the polishing process parameters and the polishing result.
Further, the optimizing the BP neural network according to the adaptive particle population algorithm to obtain an adaptive optimization algorithm includes:
creating a BP neural network and determining the structure of the BP neural network;
generating an initial population according to the input polishing process parameters;
calculating an initial fitness value of the initial population, and setting an individual optimal value and a global optimal value;
and continuously iterating and updating to obtain an optimal weight and a threshold, wherein the optimal weight and the threshold are used for optimizing the initial weight and the threshold of the BP neural network.
Further, the constructing the SPSO-BP prediction model according to the adaptive optimization algorithm includes:
learning and training the BP neural network according to the test data;
and continuously optimizing the initial weight and the threshold value according to the learning and training results and the optimal weight and the threshold value optimized by the self-adaptive particle population algorithm until the termination condition is met, and obtaining the SPSO-BP prediction model.
Further, the adaptive particle population algorithm comprises a particle population algorithm based on adaptive weight of a Sigmod function, wherein an expression of the Sigmod function is as follows:
wherein the Sigmod function is approximately sigmoidal in shape and symmetric about the (μ, γ/2) center, the curve growing faster at the center and slower at both ends.
Further, the continuously iterating and updating to obtain an optimal weight and a threshold, where the optimal weight and the threshold are used to optimize the initial weight and the threshold, including:
updating the flying speed and position of the particles according to the individual optimal value and the global optimal value;
updating the individual optimality and the global optimum;
and continuously and repeatedly dividing the steps by calculating the inertia weight and updating the learning factor until the optimal weight and the threshold are obtained.
Further, the expression of the inertia weight coefficient constructed based on the Sigmod function is:
wherein the values of μ and γ are set according to the following equations:
further, the expression of the inertial weight is:
wherein, at the beginning of iteration, the inertial weight approaches epsilon infinitelymax；
In the middle of the iteration, the inertia weight is (ε)min+εmax)/2；
At the end of the iteration, the inertial weight approaches ε infinitelymin。
Further, the acquiring of the polishing process parameters and the corresponding test data of the polishing result includes:
and acquiring test data of different polishing process parameter combinations of different plates and polishing results respectively corresponding to the different polishing process parameter combinations.
Further, the polishing process parameters include: polishing pressure, polishing rotating speed, abrasive particle diameter and abrasive particle number in unit volume; the polishing results include surface roughness values and polishing efficiencies.
The invention provides a metal mirror polishing process parameter self-adaptive matching method, which is based on a SPSO-BP prediction model combined by a self-adaptive weight particle population algorithm SPSO and a BP neural network algorithm, and self-adaptively matches mirror polishing process parameters according to different material attributes, mirror polishing quality and efficiency requirements to obtain an ideal surface roughness value and polishing efficiency, thereby providing a theoretical basis for actual precision polishing operation. The method solves the problems that the workload of manual tests in the prior mirror polishing period is large, and the cost of defective parts generated in the tests is high, and the method does not depend on subjective experience, thereby reducing the requirements on the experience of operators.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method for adaptively matching parameters of a metal mirror polishing process provided by the present invention.
Fig. 2 is a flowchart of a specific process for optimizing the BP neural network according to the adaptive particle population algorithm provided in the present invention.
Fig. 3 is a schematic diagram of a BP neural network structure provided by the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this embodiment, a method for adaptively matching parameters of a metal mirror polishing process is provided, and fig. 1 is a flowchart of a method for adaptively matching parameters of a metal mirror polishing process according to an embodiment of the present invention, as shown in fig. 1, including:
s110, obtaining polishing process parameters and test data of corresponding polishing results;
it should be understood that, in the embodiment of the present invention, the obtaining of the test data of different combinations of polishing process parameters of different plates and their corresponding polishing results may be specifically included.
Namely, a plurality of different plates can be obtained, and polishing results can be obtained under different polishing process parameter combinations.
For example, A, B and C plates were obtained, which were polished under different combinations of polishing process parameters.
In an embodiment of the present invention, the polishing process parameters include: polishing pressure, polishing rotating speed, abrasive particle diameter and abrasive particle number in unit volume; the polishing results include surface roughness values and polishing efficiencies.
It should be understood that the different polishing process parameter combinations may be specifically a combination of changes in any one or more of polishing pressure, polishing rotation speed, abrasive particle diameter and abrasive particle number per unit volume.
The test data may be obtained by performing preliminary tests, such as selecting various different combinations of polishing process parameters, polishing a metal plate and recording the polishing time, and measuring the initial roughness R of the workpiece by using a roughness testera0And roughness value R of the polished workpieceazAnd measuring the thickness difference Th before and after the polishing of the plate by using a thickness gauge, and recording process parameters and results as training samples.
S120, constructing a prediction model according to a self-adaptive optimization algorithm, wherein the prediction model can carry out self-learning according to the test data to obtain the mapping relation between the polishing process parameters and the polishing result;
it should be understood that an SPSO-BP prediction model can be constructed in Matlab, and the potential rules of surface roughness, material removal and process parameters are obtained through functional analysis such as self-learning and self-organization of the model.
In the embodiment of the present invention, the SPSO-BP prediction model may specifically refer to a prediction model based on a combination of a Sigmod function adaptive particle population algorithm (SPSO) and a BP neural network algorithm.
Specifically, the building of the prediction model according to the adaptive optimization algorithm includes:
optimizing the BP neural network according to a self-adaptive particle population algorithm to obtain a self-adaptive optimization algorithm;
constructing an SPSO-BP prediction model according to the self-adaptive optimization algorithm;
the SPSO-BP prediction model can carry out self-learning according to the test data to obtain the mapping relation between the polishing process parameters and the polishing result.
As shown in fig. 2, a specific process of obtaining the adaptive optimization algorithm and constructing the SPSO-BP prediction model is performed for optimizing the BP neural network according to the adaptive particle population algorithm.
The method specifically comprises the following steps:
creating a BP neural network and determining the structure of the BP neural network;
generating an initial population according to the input polishing process parameters;
calculating an initial fitness value of the initial population, and setting an individual optimal value and a global optimal value;
and continuously iterating and updating to obtain an optimal weight and a threshold, wherein the optimal weight and the threshold are used for optimizing the initial weight and the threshold of the BP neural network.
Wherein, the construction of the SPSO-BP prediction model according to the self-adaptive optimization algorithm comprises the following steps:
learning and training the BP neural network according to the test data;
and continuously optimizing the initial weight and the threshold value according to the learning and training results and the optimal weight and the threshold value optimized by the self-adaptive particle population algorithm until the termination condition is met, and obtaining the SPSO-BP prediction model.
It should be understood that the termination condition described herein may be specifically understood as a condition that can reach the optimal weight and threshold.
It should be noted that, when solving the problem of the optimal solution, the particle population algorithm (PSO) may obtain the optimal solution in the space based on the individual extremum and the global extremum, and the continuous iteration and the updating speed and position after generating the initial population. The update formulas of the position and the flying speed of the particle are respectively as follows:
wherein ε represents an inertial weight parameter, C1And C2All represent learning silver, n represents the current iteration number, r1And r2Is [0, 1 ]]Any number of them.
The influence performance of the inertia weight epsilon on the particle population algorithm is the largest, and the inertia weight epsilon is the key for balancing the local searching capability and the global searching capability. The inertia weight is small, so that the local optimum is easy to fall into; the larger the inertial weight, the slower the convergence speed results. Therefore, the adaptive particle population algorithm is provided by comprehensively considering the iteration times and the adaptability change.
In this embodiment of the present invention, the adaptive particle population algorithm includes a particle swarm algorithm (SPSO) based on adaptive weight of a Sigmod function, where an expression of the Sigmod function is:
wherein the Sigmod function is approximately sigmoidal in shape and symmetric about the (μ, γ/2) center, the curve growing faster at the center and slower at both ends.
In the initial stage of iteration, the algorithm should pay attention to the global search capability, the inertia weight is set to be a large value, in the later stage of iteration, the algorithm should ensure that the particles can be quickly converged to find the optimal solution, and the inertia weight is set to be a small value.
In this embodiment of the present invention, the continuously iterating and updating to obtain an optimal weight and a threshold, where the optimal weight and the threshold are used to optimize the initial weight and the threshold, and the method includes:
updating the flying speed and position of the particles according to the individual optimal value and the global optimal value;
updating the individual optimality and the global optimum;
and continuously and repeatedly dividing the steps by calculating the inertia weight and updating the learning factor until the optimal weight and the threshold are obtained.
Specifically, the expression of the inertia weight coefficient constructed based on the Sigmod function is:
wherein the values of μ and γ are set according to the following equations:
setting mu to 1/2T, and enabling the particles to take the middle iteration point as a symmetrical point; gamma is set according to the self fitness of the particles and the average fitness of the population, and when the fitness value of the particles is low, the optimization step is reduced, and the local search capability is increased; when the fitness value of the particle swarm is larger and the difference between the fitness value of the particle swarm and the population is larger, the global search capability is improved, and the expression of the inertia weight is as follows:
wherein, in the initial stage of iteration, the algorithm focuses on searching in the global scope, the inertia weight epsilon (x) is as large as possible and is infinitely close to epsilonmax；
In the early stage of iteration, the particle can properly increase the local searching capability, but still takes the global searching capability as the main;
in the middle of the iteration, the inertia weight is (ε)min+εmax) At the moment, the inertia weight of the particles is rapidly reduced, and the particles are in a transition stage from global search to local search;
in the middle and later period of iteration, the inertia weight is further reduced, the particles continue to be searched from the global position to the local position, and the local search is taken as the main point;
at the end of the iteration, the inertial weight approaches ε infinitelyminAnd the particles are focused on local search to complete the whole iterative process.
Aiming at learning factor C in the formula (1)1And C2(C1Represents the individual optimal learning factor, C2Representing population-optimal learning factors) are set in the embodiment of the present invention as follows:
when f is less than or equal to favgWhen the particle is in a good position, the particle should enhance its learning, so C can be set1＝3，C22; when f is>favgWhen the position of the particle is poor, the particle should focus on the population learning to strengthen the connection between the particle and the population, so C can be set1＝2，C2＝3。
S130, inputting the target polishing result into the prediction model to obtain a result of simulation prediction of the prediction model;
in the embodiment of the invention, the BP neural network comprises two processes of forward propagation of signals and backward propagation of errors, obtains a result closest to an expected output value by combining given input values through self training and learning, and mainly comprises an input layer and a hidden layerAnd an output layer. In the actual polishing operation, the hardness H of the workpiecegModulus of elasticity E of workgModulus of elasticity E of polishing padpModulus of elasticity E of abrasive grainsmInitial surface roughness value R of workpiecea0Generally as the basic conditions, the surface roughness value Ra and the material removal rate MMR are taken as the known polishing technical requirements, so that the 6 parameters are taken as input layers, the polishing pressure F, the polishing rotating speed omega and the abrasive particle diameter DmAnd the number N of abrasive grains per unit volumemThe process parameters which are mainly adjusted in the process test are placed on an output layer, the number of hidden layers is one, nodes can be specifically selected to be 10 through an empirical formula, and therefore a three-layer neural network of 6-10-4 is established, and the BP neural network structure is shown in figure 3.
And S140, taking the result of the simulation prediction as an instructive polishing process parameter for realizing the target polishing result.
It should be understood that the target polishing result, specifically, the surface roughness value target Ra and the material removal rate target MMR are set as the inputs of the SPSO-BP prediction model, and the two prediction models are used for simulation prediction in Matlab, so as to obtain the corresponding combination of process parameters, such as the polishing rotation speed, the polishing pressure, the diameter of the abrasive grains, and the number of the abrasive grains in unit volume, and provide a basis for the actual polishing process.
In conclusion, the self-adaptive matching method for the metal mirror polishing process parameters, provided by the invention, has the advantages that the self-adaptive weight-based SPSO prediction model combined with the SPSO-BP neural network algorithm is self-adaptively matched with the mirror polishing process parameters according to different material attributes and requirements on mirror polishing quality and efficiency, so that an ideal surface roughness value and polishing efficiency are obtained, and a theoretical basis is provided for actual precise polishing operation. The method solves the problems that the workload of manual tests in the prior mirror polishing period is large, and the cost of defective parts generated in the tests is high, and the method does not depend on subjective experience, thereby reducing the requirements on the experience of operators.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (10)
1. A metal mirror polishing process parameter adaptive matching method is characterized by comprising the following steps:
obtaining polishing process parameters and test data of corresponding polishing results;
constructing a prediction model according to a self-adaptive optimization algorithm, wherein the prediction model can carry out self-learning according to the test data to obtain the mapping relation between the polishing process parameters and the polishing result;
inputting the target polishing result into the prediction model to obtain a result of simulation prediction of the prediction model;
and taking the result of the simulation prediction as an instructive polishing process parameter for realizing the target polishing result.
2. The adaptive matching method for metal mirror polishing process parameters according to claim 1, wherein the constructing a prediction model according to an adaptive optimization algorithm comprises:
optimizing the BP neural network according to a self-adaptive particle population algorithm to obtain a self-adaptive optimization algorithm;
constructing an SPSO-BP prediction model according to the self-adaptive optimization algorithm;
the SPSO-BP prediction model can carry out self-learning according to the test data to obtain the mapping relation between the polishing process parameters and the polishing result.
3. The adaptive matching method for parameters of metal mirror polishing process according to claim 2, wherein the optimization of the BP neural network according to the adaptive particle population algorithm to obtain the adaptive optimization algorithm comprises:
creating a BP neural network and determining the structure of the BP neural network;
generating an initial population according to the input polishing process parameters;
calculating an initial fitness value of the initial population, and setting an individual optimal value and a global optimal value;
and continuously iterating and updating to obtain an optimal weight and a threshold, wherein the optimal weight and the threshold are used for optimizing the initial weight and the threshold of the BP neural network.
4. The adaptive matching method for metal mirror polishing process parameters according to claim 3, wherein the constructing of the SPSO-BP prediction model according to the adaptive optimization algorithm comprises:
learning and training the BP neural network according to the test data;
and continuously optimizing the initial weight and the threshold value according to the learning and training results and the optimal weight and the threshold value optimized by the self-adaptive particle population algorithm until the termination condition is met, and obtaining the SPSO-BP prediction model.
5. The metal mirror polishing process parameter adaptive matching method of claim 3, wherein the adaptive particle population algorithm comprises a particle swarm algorithm based on adaptive weights of a Sigmod function, wherein the expression of the Sigmod function is as follows:
wherein the Sigmod function is approximately sigmoidal in shape and symmetric about the (μ, γ/2) center, the curve growing faster at the center and slower at both ends.
6. The adaptive matching method for metal mirror polishing process parameters according to claim 5, wherein the continuously iterating and updating to obtain optimal weights and thresholds, the optimal weights and thresholds being used to optimize the initial weights and thresholds, comprises:
updating the flying speed and position of the particles according to the individual optimal value and the global optimal value;
updating the individual optimality and the global optimum;
and continuously and repeatedly dividing the steps by calculating the inertia weight and updating the learning factor until the optimal weight and the threshold are obtained.
7. The adaptive matching method for metal mirror polishing process parameters according to claim 6, wherein the expression of the inertia weight coefficients constructed based on the Sigmod function is:
wherein the values of μ and γ are set according to the following equations:
8. the adaptive matching method for metal mirror polishing process parameters according to claim 7, wherein the expression of the inertial weight is:
wherein, at the beginning of iteration, the inertial weight approaches epsilon infinitelymax；
In the middle of the iteration, the inertia weight is (ε)min+εmax)/2；
At the end of the iteration, the inertial weight approaches ε infinitelymin。
9. The adaptive matching method for metal mirror polishing process parameters according to claim 1, wherein the obtaining of the polishing process parameters and the corresponding test data of the polishing results comprises:
and acquiring test data of different polishing process parameter combinations of different plates and polishing results respectively corresponding to the different polishing process parameter combinations.
10. The adaptive matching method for metal mirror polishing process parameters according to claim 1, wherein the polishing process parameters comprise: polishing pressure, polishing rotating speed, abrasive particle diameter and abrasive particle number in unit volume; the polishing results include surface roughness values and polishing efficiencies.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011543.8A CN114330142A (en) | 2022-01-06 | 2022-01-06 | Self-adaptive matching method for metal mirror polishing process parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011543.8A CN114330142A (en) | 2022-01-06 | 2022-01-06 | Self-adaptive matching method for metal mirror polishing process parameters |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114330142A true CN114330142A (en) | 2022-04-12 |
Family
ID=81025077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210011543.8A Pending CN114330142A (en) | 2022-01-06 | 2022-01-06 | Self-adaptive matching method for metal mirror polishing process parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114330142A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116551474A (en) * | 2023-06-08 | 2023-08-08 | 上海弘智金属制品有限公司 | Optimized polishing method and system for aluminum alloy die castings |
| CN117226608A (en) * | 2023-09-19 | 2023-12-15 | 中山市光大光学仪器有限公司 | Polishing control method and system for beam-splitting prism coating film |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110532588A (en) * | 2019-07-11 | 2019-12-03 | 华南理工大学 | A kind of three-dimensional class cycloid intelligence polishing method of Hilbert curve guidance |
| CN111468989A (en) * | 2020-03-30 | 2020-07-31 | 黄河水利职业技术学院 | Five-axis linkage numerical control manipulator polishing control system and method |
| CN112580253A (en) * | 2020-11-26 | 2021-03-30 | 广东工业大学 | Method for detecting mechanical properties of plasma cladding wear-resistant toughening coating on surface of high manganese steel |
-
2022
- 2022-01-06 CN CN202210011543.8A patent/CN114330142A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110532588A (en) * | 2019-07-11 | 2019-12-03 | 华南理工大学 | A kind of three-dimensional class cycloid intelligence polishing method of Hilbert curve guidance |
| CN111468989A (en) * | 2020-03-30 | 2020-07-31 | 黄河水利职业技术学院 | Five-axis linkage numerical control manipulator polishing control system and method |
| CN112580253A (en) * | 2020-11-26 | 2021-03-30 | 广东工业大学 | Method for detecting mechanical properties of plasma cladding wear-resistant toughening coating on surface of high manganese steel |
Non-Patent Citations (1)
| Title |
|---|
| 杨志贤: "基于PSO-BP神经网络的磨削表面粗糙度预测模型的研究", 《工具技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116551474A (en) * | 2023-06-08 | 2023-08-08 | 上海弘智金属制品有限公司 | Optimized polishing method and system for aluminum alloy die castings |
| CN116551474B (en) * | 2023-06-08 | 2024-03-05 | 上海弘智金属制品有限公司 | Optimized polishing method and system for aluminum alloy die castings |
| CN117226608A (en) * | 2023-09-19 | 2023-12-15 | 中山市光大光学仪器有限公司 | Polishing control method and system for beam-splitting prism coating film |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114330142A (en) | Self-adaptive matching method for metal mirror polishing process parameters | |
| CN110405343B (en) | Laser welding process parameter optimization method based on Bagging integrated prediction model and particle swarm optimization algorithm | |
| CN108942409A (en) | The modeling and monitoring method of tool abrasion based on residual error convolutional neural networks | |
| CN111633467B (en) | Cutter wear state monitoring method based on one-dimensional depth convolution automatic encoder | |
| CN109670580A (en) | A kind of data recovery method based on time series | |
| CN113191484A (en) | Federal learning client intelligent selection method and system based on deep reinforcement learning | |
| US6564116B2 (en) | Method for determining efficiently parameters in chemical-mechanical polishing (CMP) | |
| CN108632764B (en) | Multi-sensor selective measurement data fusion estimation method | |
| CN111752151A (en) | Adaptive tracking and compensating method and system for grinding and polishing industrial blade | |
| CN112504533A (en) | Characterization method of film-substrate interface residual stress | |
| CN115270867A (en) | Improved DQN fault diagnosis method and system for gas turbine rotor system | |
| CN116362329A (en) | Cluster federation learning method and device integrating parameter optimization | |
| CN115438589A (en) | Fishing rod adjustability prediction model based on BP neural network and optimization method thereof | |
| Natarajan et al. | Production wastage avoidance using modified multi-objective teaching learning based optimization embedded with refined learning scheme | |
| CN116910485A (en) | Rotary machine fault diagnosis method based on IMPA-VMD energy entropy and improved BiGRU | |
| CN114880806A (en) | New energy automobile sales prediction model parameter optimization method based on particle swarm optimization | |
| CN112199637B (en) | Regression modeling method for generating contrast network data enhancement based on regression attention | |
| CN117370766A (en) | Satellite mission planning scheme evaluation method based on deep learning | |
| CN116976192A (en) | JS-BP model-based die forging defect accurate repair process parameter decision method | |
| Natarajan et al. | Application of particle swarm optimisation in artificial neural network for the prediction of tool life | |
| CN116668068A (en) | Industrial control abnormal flow detection method based on joint federal learning | |
| CN116342789A (en) | Layered material rendering method and device based on meta learning | |
| CN113673166B (en) | Digital twin model working condition self-adaption method and system for processing quality prediction | |
| CN113221954B (en) | Method for detecting surface defects of strip steel by using improved bat algorithm | |
| CN115100233A (en) | Radar target tracking method based on generation of confrontation network resampling particle filter |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220412 |
|
| RJ01 | Rejection of invention patent application after publication |